AsianPlayer/TriDrive / benchmark /tables /aide_extra /driverwm_quantile_sweep.json
AsianPlayer's picture
download
raw
34.5 kB
{
"generated_utc": "20260917T071328Z",
"script": "aide/eval/report_driverwm_quantile_sweep.py",
"source": {
"hm_subsets_json_generated_utc": "20260915T031542Z",
"hm_subsets_prereg_utc": "2026-09-15T03:01:43Z",
"prereg_this_table": "docs/decisions.md row 2026-09-17T07:00:22Z (B)"
},
"subsets": {
"q005": {
"q": 0.05,
"n": 30,
"threshold": 97.43711615088908,
"mean_score": 201.3462602116006
},
"q010": {
"q": 0.1,
"n": 60,
"threshold": 72.05217866513287,
"mean_score": 140.9006354784163
},
"q020": {
"q": 0.2,
"n": 121,
"threshold": 55.35391204400551,
"mean_score": 101.77845066157111
},
"q030": {
"q": 0.3,
"n": 182,
"threshold": 42.00118575469195,
"mean_score": 83.64832321345706
},
"q050": {
"q": 0.5,
"n": 304,
"threshold": 28.002438908122684,
"mean_score": 63.90251204541458
},
"q100": {
"q": 1.0,
"n": 609,
"threshold": 5.493227177401432,
"mean_score": 40.481117169152306
}
},
"levels_avg": {
"zv": {
"q005": {
"mean": 175.6591381694212,
"sd": null,
"n": 1
},
"q010": {
"mean": 139.2275099328958,
"sd": null,
"n": 1
},
"q020": {
"mean": 111.53943198247612,
"sd": null,
"n": 1
},
"q030": {
"mean": 97.1578353266867,
"sd": null,
"n": 1
},
"q050": {
"mean": 79.36304788883217,
"sd": null,
"n": 1
},
"q100": {
"mean": 52.929251806279915,
"sd": null,
"n": 1
}
},
"K": {
"q005": {
"mean": 166.12721252118942,
"sd": 0.8145127699158533,
"n": 5
},
"q010": {
"mean": 131.57298399066454,
"sd": 0.5708489438606231,
"n": 5
},
"q020": {
"mean": 103.9716273964032,
"sd": 0.5899459149636878,
"n": 5
},
"q030": {
"mean": 91.00484744950815,
"sd": 0.39444632570382304,
"n": 5
},
"q050": {
"mean": 74.00839533694727,
"sd": 0.265747966369039,
"n": 5
},
"q100": {
"mean": 48.60106917001819,
"sd": 0.11660801168013415,
"n": 5
}
},
"Kpre": {
"q005": {
"mean": 163.84835670724635,
"sd": 0.876998888287253,
"n": 5
},
"q010": {
"mean": 128.82312471721852,
"sd": 0.3888509288982342,
"n": 5
},
"q020": {
"mean": 102.48266418661967,
"sd": 0.38126902298587223,
"n": 5
},
"q030": {
"mean": 89.80601986235446,
"sd": 0.2579798228980628,
"n": 5
},
"q050": {
"mean": 73.09625186838193,
"sd": 0.137918391087891,
"n": 5
},
"q100": {
"mean": 48.051469856123596,
"sd": 0.06201440075086556,
"n": 5
}
},
"KS": {
"q005": {
"mean": 164.91978556493893,
"sd": 1.4881121907772294,
"n": 3
},
"q010": {
"mean": 130.2803576705643,
"sd": 0.8586999152845723,
"n": 3
},
"q020": {
"mean": 103.40241915370382,
"sd": 0.49158500376106823,
"n": 3
},
"q030": {
"mean": 90.68365726029198,
"sd": 0.5045137681963433,
"n": 3
},
"q050": {
"mean": 73.68680699995203,
"sd": 0.30082524216865636,
"n": 3
},
"q100": {
"mean": 48.36366613889913,
"sd": 0.17280581176681964,
"n": 3
}
},
"DWMrepro": {
"q005": {
"mean": 206.85155130952725,
"sd": 3.910288536992271,
"n": 3
},
"q010": {
"mean": 176.3320167842904,
"sd": 3.2897914287794574,
"n": 3
},
"q020": {
"mean": 157.20300842432263,
"sd": 3.2895706341551865,
"n": 3
},
"q030": {
"mean": 149.0634015176566,
"sd": 3.288137311029449,
"n": 3
},
"q050": {
"mean": 141.435795957375,
"sd": 3.308546533956452,
"n": 3
},
"q100": {
"mean": 130.86487703772423,
"sd": 3.1119325708516876,
"n": 3
}
},
"DWMkp": {
"q005": {
"mean": 168.27135584937122,
"sd": 0.9878906847741302,
"n": 3
},
"q010": {
"mean": 132.92455175660166,
"sd": 0.8742846056068947,
"n": 3
},
"q020": {
"mean": 106.43968906736923,
"sd": 0.6479657025251124,
"n": 3
},
"q030": {
"mean": 93.38843088140784,
"sd": 0.6336142191632909,
"n": 3
},
"q050": {
"mean": 76.23818651434631,
"sd": 0.5367330369114358,
"n": 3
},
"q100": {
"mean": 50.64701339210948,
"sd": 0.29266149051626217,
"n": 3
}
}
},
"levels_h5": {
"zv": {
"q005": {
"mean": 230.27594715009664,
"sd": null,
"n": 1
},
"q010": {
"mean": 178.6652573554072,
"sd": null,
"n": 1
},
"q020": {
"mean": 140.6624159993732,
"sd": null,
"n": 1
},
"q030": {
"mean": 120.4580059682737,
"sd": null,
"n": 1
},
"q050": {
"mean": 97.28426177891416,
"sd": null,
"n": 1
},
"q100": {
"mean": 63.73992862314449,
"sd": null,
"n": 1
}
},
"K": {
"q005": {
"mean": 212.3391004828797,
"sd": 0.4540893333778318,
"n": 5
},
"q010": {
"mean": 163.36958915899405,
"sd": 0.6274864475488037,
"n": 5
},
"q020": {
"mean": 127.45685307963126,
"sd": 0.7737542451013978,
"n": 5
},
"q030": {
"mean": 109.85388367638613,
"sd": 0.48509968109287516,
"n": 5
},
"q050": {
"mean": 88.94488599806064,
"sd": 0.3180163098948537,
"n": 5
},
"q100": {
"mean": 57.63671166193673,
"sd": 0.1758503971298825,
"n": 5
}
},
"Kpre": {
"q005": {
"mean": 210.5062422653985,
"sd": 0.9011177057969677,
"n": 5
},
"q010": {
"mean": 159.91787957048092,
"sd": 0.9191484762261937,
"n": 5
},
"q020": {
"mean": 125.64484158773807,
"sd": 0.8548337493522166,
"n": 5
},
"q030": {
"mean": 108.52902122936146,
"sd": 0.5692909099590934,
"n": 5
},
"q050": {
"mean": 87.86509325799312,
"sd": 0.3796037352052681,
"n": 5
},
"q100": {
"mean": 57.02220314224618,
"sd": 0.1795895717848484,
"n": 5
}
},
"KS": {
"q005": {
"mean": 211.0486259291536,
"sd": 1.926538856411558,
"n": 3
},
"q010": {
"mean": 161.9296325420486,
"sd": 0.8379485151089465,
"n": 3
},
"q020": {
"mean": 126.91513094922705,
"sd": 0.15741811178661896,
"n": 3
},
"q030": {
"mean": 109.64240377284587,
"sd": 0.2997089952125642,
"n": 3
},
"q050": {
"mean": 88.68874865315428,
"sd": 0.19479773601906794,
"n": 3
},
"q100": {
"mean": 57.472783587563065,
"sd": 0.14495461239202395,
"n": 3
}
},
"DWMrepro": {
"q005": {
"mean": 237.83022874142102,
"sd": 3.109408631631758,
"n": 3
},
"q010": {
"mean": 194.33921280037944,
"sd": 2.6506239795760598,
"n": 3
},
"q020": {
"mean": 169.41549018621745,
"sd": 3.2792341584070193,
"n": 3
},
"q030": {
"mean": 158.09075994565993,
"sd": 3.4829616912294594,
"n": 3
},
"q050": {
"mean": 147.71053541042986,
"sd": 3.67964528612334,
"n": 3
},
"q100": {
"mean": 134.50304347622986,
"sd": 3.4567144370971605,
"n": 3
}
},
"DWMkp": {
"q005": {
"mean": 213.6259650311741,
"sd": 1.5524374737464905,
"n": 3
},
"q010": {
"mean": 162.82809632225994,
"sd": 1.132707797580306,
"n": 3
},
"q020": {
"mean": 129.74240062220687,
"sd": 0.9244255551777524,
"n": 3
},
"q030": {
"mean": 112.44366283655181,
"sd": 0.8461496195254132,
"n": 3
},
"q050": {
"mean": 91.41505043596885,
"sd": 0.6904088461476124,
"n": 3
},
"q100": {
"mean": 60.04347665869512,
"sd": 0.3971635079082248,
"n": 3
}
}
},
"published": {
"seed42": {
"label": "Driver-WM published, single run (v2 Table 1 / Table 7 seed 42; text / Tables 10\u201311 for h=5)",
"avg": {
"q010": "138.03",
"q100": "71.47"
},
"h5": {
"q010": "155.82"
},
"src": "driverwm_v2_audit.md:23 (71.47 / 138.03), :56 and :58 (155.82)"
},
"seeds3": {
"label": "Driver-WM published, 3-seed mean \u00b1 sd (v2 Table 8, seeds 42/123/456)",
"avg": {
"q010": "138.34 \u00b1 1.2",
"q100": "71.66 \u00b1 0.3"
},
"h5": {},
"src": "driverwm_v2_audit.md:235"
}
},
"delta_h5": {
"K_vs_DWMkp": {
"q005": {
"n": 3,
"h5_mean": -1.406595511338739,
"h5_sd": 1.270773504377561,
"h5_k": 0,
"h5_per_seed": [
[
"42",
-0.10089720657113427,
-8.270973568240516,
8.283499322746554
],
[
"123",
-2.6392974485940806,
-10.021198166758639,
4.432901835627183
],
[
"456",
-1.4795918788510023,
-8.312229888110501,
4.531486636880362
]
],
"avg_mean": -1.9380694422939984,
"avg_sd": 2.0179771389083725,
"avg_k": 0,
"verdict": "INCONCLUSIVE"
},
"q010": {
"n": 3,
"h5_mean": 0.5392345370228081,
"h5_sd": 1.9559173761959974,
"h5_k": 0,
"h5_per_seed": [
[
"42",
2.4736427412986988,
-3.285366469886823,
8.318637390416484
],
[
"123",
0.5815657026828867,
-4.154122650659311,
5.049322713005648
],
[
"456",
-1.437504832913161,
-6.630881864344249,
3.441743145389341
]
],
"avg_mean": -1.2862008960588456,
"avg_sd": 1.597840338688109,
"avg_k": 0,
"verdict": "INCONCLUSIVE"
},
"q020": {
"n": 3,
"h5_mean": -2.1563998579781325,
"h5_sd": 1.9788526161634523,
"h5_k": 1,
"h5_per_seed": [
[
"42",
-0.34589582932803403,
-3.6920397974814345,
3.2532420117802805
],
[
"123",
-1.8544178236704147,
-4.770558137886788,
1.10079400830447
],
[
"456",
-4.268885920935949,
-7.384441150631762,
-1.150731040555883
]
],
"avg_mean": -2.318295373558902,
"avg_sd": 1.420454693011974,
"avg_k": 2,
"verdict": "BEATS"
},
"q030": {
"n": 3,
"h5_mean": -2.502022060474458,
"h5_sd": 1.5092228869038429,
"h5_k": 2,
"h5_per_seed": [
[
"42",
-1.1527698151578603,
-3.625489362123885,
1.3453583286832396
],
[
"123",
-2.221455790870622,
-4.372396687975145,
-0.16858091489063026
],
[
"456",
-4.131840575394891,
-6.4337034465842935,
-1.9480803519688206
]
],
"avg_mean": -2.3756810842030665,
"avg_sd": 1.1320841699249116,
"avg_k": 2,
"verdict": "BEATS"
},
"q050": {
"n": 3,
"h5_mean": -2.440313172158199,
"h5_sd": 1.135523325909029,
"h5_k": 2,
"h5_per_seed": [
[
"42",
-1.4491598560199777,
-2.995315314983932,
0.16285483831407047
],
[
"123",
-2.1925026151000524,
-3.5196860986196166,
-0.800988480390926
],
[
"456",
-3.6792770453545662,
-5.205705476072623,
-2.158787609894615
]
],
"avg_mean": -2.1910777919201263,
"avg_sd": 0.8654689740073076,
"avg_k": 3,
"verdict": "BEATS"
},
"q100": {
"n": 3,
"h5_mean": -2.390867402782266,
"h5_sd": 0.6313708572556406,
"h5_k": 3,
"h5_per_seed": [
[
"42",
-1.9674511953845708,
-2.897140807790335,
-1.041319694563202
],
[
"123",
-2.088602554005561,
-2.8538722030979793,
-1.299943211741429
],
[
"456",
-3.116548458956666,
-4.0303140408057825,
-2.2345112134112206
]
],
"avg_mean": -2.0170857795171275,
"avg_sd": 0.4469668678810056,
"avg_k": 3,
"verdict": "BEATS"
}
},
"Kpre_vs_DWMkp": {
"q005": {
"n": 3,
"h5_mean": -3.369510399638172,
"h5_sd": 1.019261580865899,
"h5_k": 0,
"h5_per_seed": [
[
"42",
-2.311243661957414,
-10.167440496148542,
5.687815920236578
],
[
"123",
-3.4526081150066052,
-9.850682390875658,
2.7317562940502893
],
[
"456",
-4.344679421950497,
-9.972813953856974,
1.0475649171183752
]
],
"avg_mean": -4.2692277287625195,
"avg_sd": 1.2498622614933188,
"avg_k": 2,
"verdict": "BEATS"
},
"q010": {
"n": 3,
"h5_mean": -3.3367151059343456,
"h5_sd": 1.420176476574115,
"h5_k": 1,
"h5_per_seed": [
[
"42",
-2.371808120710614,
-7.31225994847416,
2.6162527714091453
],
[
"123",
-2.670858053870119,
-7.332140578469865,
1.9070036297298043
],
[
"456",
-4.967479143222304,
-9.357988045735917,
-0.6791771141343068
]
],
"avg_mean": -4.236265259580185,
"avg_sd": 0.7927791397335783,
"avg_k": 3,
"verdict": "BEATS"
},
"q020": {
"n": 3,
"h5_mean": -4.1128558539589815,
"h5_sd": 1.4198229521859804,
"h5_k": 3,
"h5_per_seed": [
[
"42",
-3.7103550321801357,
-6.847055923208812,
-0.5264061628456997
],
[
"123",
-2.9377371167254784,
-5.711482897774387,
-0.18457623247077712
],
[
"456",
-5.69047541297133,
-8.629151907470002,
-2.701897040218507
]
],
"avg_mean": -3.9597794134284547,
"avg_sd": 0.7528642143944692,
"avg_k": 3,
"verdict": "BEATS"
},
"q030": {
"n": 3,
"h5_mean": -4.047457982881542,
"h5_sd": 1.2179850013215774,
"h5_k": 3,
"h5_per_seed": [
[
"42",
-3.586173776949994,
-5.94334786420643,
-1.3420250595735332
],
[
"123",
-3.1274914971157273,
-5.205202655817198,
-1.1100257458452705
],
[
"456",
-5.428708674578905,
-7.583675619958659,
-3.333973616066199
]
],
"avg_mean": -3.6795156444997565,
"avg_sd": 0.7458891059979414,
"avg_k": 3,
"verdict": "BEATS"
},
"q050": {
"n": 3,
"h5_mean": -3.6589327243980847,
"h5_sd": 0.9390237716804819,
"h5_k": 3,
"h5_per_seed": [
[
"42",
-3.222337434247079,
-4.723393030597626,
-1.725633790995511
],
[
"123",
-3.017693250877475,
-4.418877409651474,
-1.5822565598264662
],
[
"456",
-4.7367674880697,
-6.219443801582367,
-3.2522004003164424
]
],
"avg_mean": -3.2009512952031733,
"avg_sd": 0.5428438947649925,
"avg_k": 3,
"verdict": "BEATS"
},
"q100": {
"n": 3,
"h5_mean": -3.099217353540231,
"h5_sd": 0.5023657994170942,
"h5_k": 3,
"h5_per_seed": [
[
"42",
-2.8206840296555784,
-3.669444591328789,
-1.9705870124999578
],
[
"123",
-2.797818851170354,
-3.6362495998649202,
-1.971689649891015
],
[
"456",
-3.6791491797947615,
-4.558583749484164,
-2.8141566667139912
]
],
"avg_mean": -2.6378276522615103,
"avg_sd": 0.28586701572476686,
"avg_k": 3,
"verdict": "BEATS"
}
},
"KS_vs_DWMkp": {
"q005": {
"n": 3,
"h5_mean": -2.5773391020204968,
"h5_sd": 2.8266349568449374,
"h5_k": 0,
"h5_per_seed": [
[
"42",
0.31884169780973437,
-7.566735888771995,
8.685473968633955
],
[
"123",
-2.721984926865839,
-8.865442523219716,
3.5346210313556403
],
[
"456",
-5.328874077005386,
-12.379394570798043,
1.1781053492794484
]
],
"avg_mean": -3.35157028443226,
"avg_sd": 1.903442810162656,
"avg_k": 1,
"verdict": "INCONCLUSIVE"
},
"q010": {
"n": 3,
"h5_mean": -0.8984637802113725,
"h5_sd": 1.9621852652792167,
"h5_k": 0,
"h5_per_seed": [
[
"42",
1.1109183600701018,
-3.4507249618320954,
5.818777947130009
],
[
"123",
-0.9965355388341769,
-5.332280507154122,
3.22176193013189
],
[
"456",
-2.8097741618700427,
-7.6721529712220295,
1.7367815955837644
]
],
"avg_mean": -2.644194086037349,
"avg_sd": 1.2949718178086729,
"avg_k": 1,
"verdict": "INCONCLUSIVE"
},
"q020": {
"n": 3,
"h5_mean": -2.827269672979829,
"h5_sd": 0.928472603405104,
"h5_k": 1,
"h5_per_seed": [
[
"42",
-2.0625134685466353,
-5.214447974569277,
1.0407176050896207
],
[
"123",
-2.5589386726709176,
-5.478578175897651,
0.34663877963332634
],
[
"456",
-3.8603568777219346,
-6.926345806777361,
-0.8018386450109585
]
],
"avg_mean": -3.0372699136654355,
"avg_sd": 0.8202835152721788,
"avg_k": 3,
"verdict": "BEATS"
},
"q030": {
"n": 3,
"h5_mean": -2.801259063705931,
"h5_sd": 0.897829630135429,
"h5_k": 3,
"h5_per_seed": [
[
"42",
-2.299789727436373,
-4.653297606872439,
-0.07172310686655026
],
[
"123",
-2.26618559792051,
-4.440913918476227,
-0.20594261147903994
],
[
"456",
-3.837801865760911,
-6.026895298420668,
-1.732613760711508
]
],
"avg_mean": -2.704773621115855,
"avg_sd": 0.8679103026041127,
"avg_k": 3,
"verdict": "BEATS"
},
"q050": {
"n": 3,
"h5_mean": -2.726301782814572,
"h5_sd": 0.7280537420800632,
"h5_k": 3,
"h5_per_seed": [
[
"42",
-2.279284767487242,
-3.7210562480735376,
-0.8232024936963479
],
[
"123",
-2.333211480584262,
-3.7333995657193135,
-0.8820998340606458
],
[
"456",
-3.5664091003722134,
-5.009317872084971,
-2.1480736794673785
]
],
"avg_mean": -2.551379514394274,
"avg_sd": 0.6627800855709784,
"avg_k": 3,
"verdict": "BEATS"
},
"q100": {
"n": 3,
"h5_mean": -2.5706930711320766,
"h5_sd": 0.4345186769238562,
"h5_k": 3,
"h5_per_seed": [
[
"42",
-2.3824653074183817,
-3.249299826935661,
-1.5367557954919164
],
[
"123",
-2.2620238695293966,
-3.13286807315665,
-1.4009902541324273
],
[
"456",
-3.0675900364484514,
-3.9247172729090622,
-2.24498436677393
]
],
"avg_mean": -2.2833472532103642,
"avg_sd": 0.380142489306515,
"avg_k": 3,
"verdict": "BEATS"
}
},
"K_vs_DWMrepro": {
"q005": {
"n": 3,
"h5_mean": -25.610859221585716,
"h5_sd": 3.125633604675596,
"h5_k": 3,
"h5_per_seed": [
[
"42",
-27.81241688669164,
-44.45570470004222,
-9.7265930577995
],
[
"123",
-22.033299551718446,
-37.009889606108025,
-6.3498215721520594
],
[
"456",
-26.98686122634707,
-43.072647837218,
-9.706490277492431
]
],
"avg_mean": -40.51826490245002,
"avg_sd": 3.5534128438020454,
"avg_k": 3,
"verdict": "BEATS"
},
"q010": {
"n": 3,
"h5_mean": -30.9718819410967,
"h5_sd": 2.8729933823577696,
"h5_k": 3,
"h5_per_seed": [
[
"42",
-31.31410658070985,
-42.76089768795937,
-19.007417795155078
],
[
"123",
-27.943104018546727,
-38.93129677726936,
-16.796544699993632
],
[
"456",
-33.65843522403352,
-44.91168573736481,
-21.943871340648588
]
],
"avg_mean": -44.69366592374754,
"avg_sd": 3.001569231216102,
"avg_k": 3,
"verdict": "BEATS"
},
"q020": {
"n": 3,
"h5_mean": -41.82948942198874,
"h5_sd": 3.6274003074607664,
"h5_k": 3,
"h5_per_seed": [
[
"42",
-42.75299799017757,
-50.802257034935785,
-34.30201383640441
],
[
"123",
-37.82960258894597,
-45.56639173413871,
-29.932782330272104
],
[
"456",
-44.90586768684269,
-52.49118488973166,
-37.162285702493165
]
],
"avg_mean": -53.08161473051231,
"avg_sd": 3.3104653238725072,
"avg_k": 3,
"verdict": "BEATS"
},
"q030": {
"n": 3,
"h5_mean": -48.14911916958258,
"h5_sd": 3.604630031478971,
"h5_k": 3,
"h5_per_seed": [
[
"42",
-49.60908215361883,
-55.70929333468284,
-43.19843478558384
],
[
"123",
-44.043528291427926,
-50.240135123605036,
-37.814037308872145
],
[
"456",
-50.794747063700996,
-56.82464273574949,
-44.74681862341365
]
],
"avg_mean": -58.05065172045181,
"avg_sd": 3.2171261544347187,
"avg_k": 3,
"verdict": "BEATS"
},
"q050": {
"n": 3,
"h5_mean": -58.73579814661923,
"h5_sd": 3.809102933799527,
"h5_k": 3,
"h5_per_seed": [
[
"42",
-60.128722351324946,
-65.68656664728859,
-54.47889656086516
],
[
"123",
-54.426292067196776,
-60.29234700517966,
-48.74192893180931
],
[
"456",
-61.652380021335965,
-67.20139633891777,
-56.19184971403079
]
],
"avg_mean": -67.38868723494882,
"avg_sd": 3.2618150905194114,
"avg_k": 3,
"verdict": "BEATS"
},
"q100": {
"n": 3,
"h5_mean": -76.85043422031698,
"h5_sd": 3.611096725239164,
"h5_k": 3,
"h5_per_seed": [
[
"42",
-78.46795600691287,
-82.62818162502597,
-74.43002239546223
],
[
"123",
-72.71334987346938,
-77.08519861672899,
-68.4503689641393
],
[
"456",
-79.36999678056871,
-83.4683835911139,
-75.37614281492077
]
],
"avg_mean": -82.23494942513186,
"avg_sd": 3.1738017935419665,
"avg_k": 3,
"verdict": "BEATS"
}
},
"Kpre_vs_DWMrepro": {
"q005": {
"n": 3,
"h5_mean": -27.57377410988515,
"h5_sd": 4.09473482037411,
"h5_k": 3,
"h5_per_seed": [
[
"42",
-30.022763342077916,
-46.26284143957916,
-12.968827655989172
],
[
"123",
-22.846610218130973,
-36.888997771149256,
-8.437914057187276
],
[
"456",
-29.851948769446565,
-44.34703530900366,
-14.6242065593044
]
],
"avg_mean": -42.849423188918536,
"avg_sd": 4.962951239340753,
"avg_k": 3,
"verdict": "BEATS"
},
"q010": {
"n": 3,
"h5_mean": -34.84783158405385,
"h5_sd": 3.204547782649699,
"h5_k": 3,
"h5_per_seed": [
[
"42",
-36.15955744271917,
-47.118424991176944,
-24.94608284762178
],
[
"123",
-31.195527775099727,
-41.64615267068476,
-20.862869616109176
],
[
"456",
-37.188409534342654,
-47.798564873827644,
-26.264232128149946
]
],
"avg_mean": -47.64373028726888,
"avg_sd": 3.6528644217832986,
"avg_k": 3,
"verdict": "BEATS"
},
"q020": {
"n": 3,
"h5_mean": -43.78594541796959,
"h5_sd": 4.221468202544197,
"h5_k": 3,
"h5_per_seed": [
[
"42",
-46.11745719302968,
-53.52133220239874,
-38.5914622472685
],
[
"123",
-38.91292188200104,
-46.08864587234121,
-31.611767169485937
],
[
"456",
-46.32745717887808,
-53.38357293326277,
-39.19625795538893
]
],
"avg_mean": -54.72309877038185,
"avg_sd": 3.7817168579687266,
"avg_k": 3,
"verdict": "BEATS"
},
"q030": {
"n": 3,
"h5_mean": -49.69455509198966,
"h5_sd": 4.109356248816176,
"h5_k": 3,
"h5_per_seed": [
[
"42",
-52.04248611541096,
-57.77914282319899,
-46.296460861510816
],
[
"123",
-44.94956399767303,
-50.8425180154306,
-39.108927913776874
],
[
"456",
-52.091615162885006,
-57.688267480586916,
-46.44244329990982
]
],
"avg_mean": -59.354486280748496,
"avg_sd": 3.5970454054010585,
"avg_k": 3,
"verdict": "BEATS"
},
"q050": {
"n": 3,
"h5_mean": -59.95441769885911,
"h5_sd": 4.092847697849739,
"h5_k": 3,
"h5_per_seed": [
[
"42",
-61.90189992955203,
-67.23144329632322,
-56.61605994475309
],
[
"123",
-55.2514827029742,
-60.834761268987904,
-49.75273209262148
],
[
"456",
-62.70987046405109,
-67.97220263406625,
-57.46327383692601
]
],
"avg_mean": -68.39856073823186,
"avg_sd": 3.4484258496239177,
"avg_k": 3,
"verdict": "BEATS"
},
"q100": {
"n": 3,
"h5_mean": -77.55878417107495,
"h5_sd": 3.5950910486142864,
"h5_k": 3,
"h5_per_seed": [
[
"42",
-79.32118884118387,
-83.34818598871112,
-75.43586239979031
],
[
"123",
-73.42256617063418,
-77.7309961014803,
-69.29448714869095
],
[
"456",
-79.9325975014068,
-83.93166886374883,
-76.03938662492656
]
],
"avg_mean": -82.85569129787625,
"avg_sd": 3.135691427299796,
"avg_k": 3,
"verdict": "BEATS"
}
},
"KS_vs_DWMrepro": {
"q005": {
"n": 3,
"h5_mean": -26.78160281226748,
"h5_sd": 4.392077132037465,
"h5_k": 3,
"h5_per_seed": [
[
"42",
-27.392677982310772,
-44.475897100325014,
-8.930706457523996
],
[
"123",
-22.115987029990205,
-37.02003432493851,
-6.3760651973035944
],
[
"456",
-30.836143424501454,
-45.776704210264654,
-15.200396873317493
]
],
"avg_mean": -41.93176574458828,
"avg_sd": 5.357711360549179,
"avg_k": 3,
"verdict": "BEATS"
},
"q010": {
"n": 3,
"h5_mean": -32.40958025833088,
"h5_sd": 2.7644552480775935,
"h5_k": 3,
"h5_per_seed": [
[
"42",
-32.67683096193845,
-44.07010741709644,
-20.8246184817733
],
[
"123",
-29.521205260063788,
-40.2340057499712,
-18.73627574488895
],
[
"456",
-35.03070455299039,
-45.633612689953864,
-24.135352127110675
]
],
"avg_mean": -46.05165911372604,
"avg_sd": 4.132917081226498,
"avg_k": 3,
"verdict": "BEATS"
},
"q020": {
"n": 3,
"h5_mean": -42.50035923699044,
"h5_sd": 3.434888928567121,
"h5_k": 3,
"h5_per_seed": [
[
"42",
-44.46961562939617,
-52.22524025420769,
-36.55530187745688
],
[
"123",
-38.53412343794648,
-45.955400148614224,
-30.874201221028596
],
[
"456",
-44.49733864362868,
-52.01415828544012,
-36.84287071390139
]
],
"avg_mean": -53.800589270618836,
"avg_sd": 3.7808389822753568,
"avg_k": 3,
"verdict": "BEATS"
},
"q030": {
"n": 3,
"h5_mean": -48.44835617281405,
"h5_sd": 3.778114331301206,
"h5_k": 3,
"h5_per_seed": [
[
"42",
-50.75610206589733,
-56.64030619071713,
-44.688121466743006
],
[
"123",
-44.088258098477816,
-50.045380101931364,
-38.0595266857787
],
[
"456",
-50.50070835406702,
-56.31409843900537,
-44.49499067156492
]
],
"avg_mean": -58.3797442573646,
"avg_sd": 3.7875180631889536,
"avg_k": 3,
"verdict": "BEATS"
},
"q050": {
"n": 3,
"h5_mean": -59.021786757275606,
"h5_sd": 3.86886681906781,
"h5_k": 3,
"h5_per_seed": [
[
"42",
-60.95884726279221,
-66.40230559836209,
-55.4962324877781
],
[
"123",
-54.567000932681,
-60.2832191958867,
-48.90607607063454
],
[
"456",
-61.53951207635361,
-67.01145836451819,
-56.055855435158705
]
],
"avg_mean": -67.74898895742297,
"avg_sd": 3.606520057787233,
"avg_k": 3,
"verdict": "BEATS"
},
"q100": {
"n": 3,
"h5_mean": -77.0302598886668,
"h5_sd": 3.595045187305998,
"h5_k": 3,
"h5_per_seed": [
[
"42",
-78.88297011894667,
-82.96489265339083,
-74.89805723238791
],
[
"123",
-72.88677118899322,
-77.21426332544667,
-68.64721501711448
],
[
"456",
-79.32103835806049,
-83.36004745757492,
-75.31398453674569
]
],
"avg_mean": -82.5012108988251,
"avg_sd": 3.2828710164063146,
"avg_k": 3,
"verdict": "BEATS"
}
}
},
"release_check": {
"checked_utc": "2026-09-17T07:03Z-07:06Z",
"method": "curl only (arXiv abs/HTML/API, GitHub REST search + repos API unauthenticated, HuggingFace Hub API, Papers-with-Code API); nothing downloaded, no weights fetched",
"verdict": "NOT RELEASED: no official code, no official weights; official project page shows a 'Code Coming Soon' button without a link",
"previous_record": "decisions.md row 2026-09-17T07:00:22Z (PRE-REG B) stated 'no code/weights' without a dated check; no earlier dated release check exists in decisions.md, so this is the first dated check",
"official": [
{
"item": "arXiv abstract page",
"url": "https://arxiv.org/abs/2605.05092",
"observed": "title 'Driver-WM: A Driver-Centric Traffic-Conditioned Latent World Model for In-Cabin Dynamics Rollout'; v1 Wed 6 May 2026 16:30:48 UTC (2,621 KB); v2 Fri 26 Jun 2026 08:53:36 UTC (2,626 KB); comment 'Accepted to the 19th European Conference on Computer Vision (ECCV 2026). This version includes the supplementary material'; no code / project link in the abstract metadata; arXiv API lists only the abs and pdf links"
},
{
"item": "arXiv HTML full text v2",
"url": "https://arxiv.org/html/2605.05092",
"observed": "the only external project link is the project page below ('Project page: Driver-WM' hyperlink on the title page of the PDF as well); no github.com / huggingface.co URL; no sentence promising or announcing a code or weight release"
},
{
"item": "official project page (GitHub Pages of first-author account fisher75, repo haozhuangchi.github.io, path driver-wm/)",
"url": "https://fisher75.github.io/haozhuangchi.github.io/driver-wm/",
"observed": "HTTP 200; buttons: 'Paper (PDF)', 'arXiv', 'Code Coming Soon' (no href), 'Video', 'Demo' (in-page figures), 'Coverage' (3 WeChat posts), 'Invited Poster', 'Workshop Details' (https://eccv26woop.github.io/), 'Watch on YouTube' (https://www.youtube.com/watch?v=wINgebPpge0); no licence text; repo tree driver-wm/ = index.html + 12 images (no .py/.pt/.zip anywhere in the repo); driver-wm/index.html last commit 2026-09-04T13:55:14Z; page Last-Modified header Wed 09 Sep 2026 20:07:40 GMT (commits of 2026-09-09 concern another project page, 'PV-WM')"
},
{
"item": "first-author GitHub account fisher75 (8 public repos)",
"url": "https://api.github.com/users/fisher75/repos",
"observed": "haozhuangchi.github.io (project pages, pushed 2026-09-09); Cabin-WM (created 2025-11-19, last push 2025-11-10, Apache-2.0) = a FORK of QwenLM/Qwen3-VL with 0 commits ahead / 17 behind upstream, README is the Qwen3-VL README, no releases/tags -> NOT a Driver-WM release; DRAMA-X (MIT, other paper); fisher75, Baselines, LLaVA fork, sglang_fork, deepxde fork (unrelated). No GitHub user 'haozhuangchi' (404)"
},
{
"item": "GitHub repository search (REST, unauthenticated)",
"url": "https://api.github.com/search/repositories",
"observed": "q=Driver-WM 34 hits, none related (window managers / WMI drivers); q=DriverWM 2 unrelated; q=2605.05092 0; q='driver-wm world model' 0; q='Driver-WM in-cabin' 0; q=Cabin-WM 1 unrelated; q='in-cabin world model' 1 = likithp82/RaWM (third party, below); q='driver world model AIDE' 0"
},
{
"item": "HuggingFace Hub (models/datasets search: driver-wm, driverwm, cabin-wm, Driver-WM; author fisher75)",
"url": "https://huggingface.co/api/models?search=driver-wm",
"observed": "no models; author fisher75 has no models; one THIRD-PARTY dataset (below)"
},
{
"item": "Papers with Code API",
"url": "https://paperswithcode.com/api/v1/papers/?arxiv_id=2605.05092",
"observed": "HTTP 302 -> https://huggingface.co/papers/trending (service discontinued; no information)"
}
],
"third_party_not_official": [
{
"item": "HF dataset Likithp/driver-wm-aide-features (author 'Likithp', not a Driver-WM author)",
"url": "https://huggingface.co/datasets/Likithp/driver-wm-aide-features",
"observed": "created 2026-07-04T04:27:34Z, last modified 2026-07-11T19:26:38Z, public, not gated, no dataset card / README, NO licence field, 170 downloads; 14,502 files: features/{train 7536, val 1620, test 2436} = per-clip front.pt / in_cabin.pt / left.pt / right.pt for 2,898 clips (= all AIDE clips; test 609), annotation/*.json x 2,898 (AIDE annotations redistributed), outputs/ and outputs_v2/ each holding baseline/seed42/{best,latest}.pt and seed42/{best,latest}.pt at 2,103.7 MB each (4 distinct LFS objects duplicated across the two folders) -> third-party checkpoints of undocumented architecture ('baseline' is not identified as Driver-WM); NOT downloaded"
},
{
"item": "GitHub likithp82/RaWM (Likith Prabhu, Mercedes-Benz R&D India; 'When Doing Nothing Wins: Motion Regime Imbalance in In-Cabin Driver Pose Forecasting', ECCV 2026 DriveX workshop)",
"url": "https://github.com/likithp82/RaWM",
"observed": "created 2026-08-14, 3 commits same day, README.md + CITATION.cff only, no code, no licence, README says 'Full dataset setup and pretrained weights coming soon'; quotes Driver-WM 71.47 / 138.03 from the paper (not a reimplementation with weights) and reports Zero-Velocity 53.42 / 140.63 and RaWM v6 51.05 +- 0.43 / 130.38 +- 0.93 (All / HM MPJPE) -> independent third-party statement that zero-velocity beats the published Driver-WM on All-MPJPE (our recomputed ZV: 52.93 / 139.23)"
}
],
"consequence": "The pre-registered branch 'if released, evaluate the released model on all quantiles under our protocol' is NOT triggered; the third-party checkpoints are not Driver-WM and have no licence, so no evaluation of them is proposed; re-check recommended before camera-ready"
},
"integrity": {
"n_mismatches": 0,
"mismatches": []
}
}

Xet Storage Details

Size:
34.5 kB
·
Xet hash:
dbb6ca7a15cedb06daca0c7516cfd5585c3434b5515175e16ce98bef35486d6e

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