YellowCab / evaluation.json
l0uai
Publish causal YellowCab benchmark and model card
52f55f8
Raw
History Blame Contribute Delete
11.9 kB
Invalid JSON:Unexpected token 'N', ..."ency_ms": NaN, "... is not valid JSON
{
"schema": "gdc_yellowcab_public_evaluation_v1",
"checkpoint": {
"source_file_sha256": "0cb9c71d5be8f7671029e459c24179863ae2abff3ccfec1b5837c169d7d6c703",
"published_file": "model.safetensors",
"published_sha256": "af1a98cd96bb68d642f7a0adeedfacac37b230917afc15f3c87230a99a15b8a2",
"training_manifest_sha256": "8b92ad563892776cc25148f39fec6bf207e1e442c618b58fb07af7e2b899364d",
"split_sha256": "bfc5e960c8af32d0ea75a5e293bb95b3125111ace2cf8452eb42feb4bc2a1a5e"
},
"causal_input_audit": {
"policy": "When past-to-current displacement is below 4 m, encode unknown current heading as sin=0 and cos=1. No future bearing is used.",
"corrected_rows": 5974,
"total_rows": 74680,
"future_derived_model_inputs": 0
},
"protocol": {
"label_type": "GPS-derived silver maneuver proxy",
"forecast_horizon": "approximately 20 seconds",
"split_policy": "Complete forward-in-time route holdout; no frame from a validation or test route enters training.",
"dataset_samples": 74680,
"dataset_routes": 36,
"test_samples": 8594,
"test_routes": 5,
"training_seed": 20260726,
"route_bootstrap_iterations": 500
},
"primary_result": {
"model": "Temporal efficientnet_b0 + telemetry",
"samples": 8594,
"accuracy": 0.5755178031184547,
"balanced_accuracy": 0.39156334041323,
"macro_f1": 0.3915542657655546,
"weighted_f1": 0.5807008272180106,
"log_loss": 1.0841176199931875,
"brier_score": 0.5563128377237149,
"ece_15_bin": 0.011817411647322817,
"p95_latency_ms": 95.37229499110252,
"continue_recall": 0.7393577296489918,
"continue_f1": 0.7492904446546831,
"slow_recall": 0.35436382754994744,
"slow_f1": 0.37716843872411865,
"stop_recall": 0.3422712933753943,
"stop_f1": 0.3580858085808581,
"turn_left_recall": 0.3157262905162065,
"turn_left_f1": 0.27568134171907754,
"turn_right_recall": 0.20609756097560974,
"turn_right_f1": 0.19754529514903565,
"macro_f1_route_ci_low": 0.34762239048615595,
"macro_f1_route_ci_high": 0.42805096076291543
},
"baselines": [
{
"model": "Temporal efficientnet_b0 + telemetry",
"samples": 8594,
"accuracy": 0.5755178031184547,
"balanced_accuracy": 0.39156334041323,
"macro_f1": 0.3915542657655546,
"weighted_f1": 0.5807008272180106,
"log_loss": 1.0841176199931877,
"brier_score": 0.5563128377237149,
"ece_15_bin": 0.0118174116473228,
"p95_latency_ms": 95.37229499110252,
"continue_recall": 0.7393577296489918,
"continue_f1": 0.7492904446546831,
"slow_recall": 0.3543638275499474,
"slow_f1": 0.3771684387241186,
"stop_recall": 0.3422712933753943,
"stop_f1": 0.3580858085808581,
"turn_left_recall": 0.3157262905162065,
"turn_left_f1": 0.2756813417190775,
"turn_right_recall": 0.2060975609756097,
"turn_right_f1": 0.1975452951490356,
"macro_f1_route_ci_low": 0.3476223904861559,
"macro_f1_route_ci_high": 0.4280509607629154
},
{
"model": "Telemetry gradient boosting",
"samples": 8594,
"accuracy": 0.4147079357691413,
"balanced_accuracy": 0.4216633099655398,
"macro_f1": 0.341392924380058,
"weighted_f1": 0.4530356863806382,
"log_loss": 1.2490630281069546,
"brier_score": 0.6566714449096165,
"ece_15_bin": 0.1216700885218681,
"p95_latency_ms": NaN,
"continue_recall": 0.4051530993278566,
"continue_f1": 0.5513911828230212,
"slow_recall": 0.6466876971608833,
"slow_f1": 0.3416666666666667,
"stop_recall": 0.4889589905362776,
"stop_f1": 0.2986512524084778,
"turn_left_recall": 0.2797118847539016,
"turn_left_f1": 0.2583148558758315,
"turn_right_recall": 0.2878048780487804,
"turn_right_f1": 0.2569406641262928,
"macro_f1_route_ci_low": 0.3149153283503967,
"macro_f1_route_ci_high": 0.3493997015446531
},
{
"model": "Vision linear (efficientnet_b0)",
"samples": 8594,
"accuracy": 0.5751687223644403,
"balanced_accuracy": 0.2967510353079744,
"macro_f1": 0.305034605073554,
"weighted_f1": 0.5344562546214928,
"log_loss": 10.24602122531317,
"brier_score": 0.8349054717132016,
"ece_15_bin": 0.4091336187074714,
"p95_latency_ms": NaN,
"continue_recall": 0.8269230769230769,
"continue_f1": 0.7406354515050168,
"slow_recall": 0.1556256572029442,
"slow_f1": 0.2148040638606676,
"stop_recall": 0.252365930599369,
"stop_f1": 0.255591054313099,
"turn_left_recall": 0.1500600240096038,
"turn_left_f1": 0.1810282404055032,
"turn_right_recall": 0.098780487804878,
"turn_right_f1": 0.1331142152834839,
"macro_f1_route_ci_low": 0.2678056005630319,
"macro_f1_route_ci_high": 0.3273143437147999
},
{
"model": "Past-motion rule",
"samples": 8594,
"accuracy": 0.4549685827321387,
"balanced_accuracy": 0.223773826591683,
"macro_f1": 0.2235297785953733,
"weighted_f1": 0.4532542316647034,
"log_loss": 2.058490921490782,
"brier_score": 0.966304980218757,
"ece_15_bin": 0.4450314172678615,
"p95_latency_ms": NaN,
"continue_recall": 0.6562733383121733,
"continue_f1": 0.6534064504136072,
"slow_recall": 0.1019978969505783,
"slow_f1": 0.0962779156327543,
"stop_recall": 0.0,
"stop_f1": 0.0,
"turn_left_recall": 0.1776710684273709,
"turn_left_f1": 0.1792852816474863,
"turn_right_recall": 0.1829268292682926,
"turn_right_f1": 0.1886792452830188,
"macro_f1_route_ci_low": 0.1873463820585989,
"macro_f1_route_ci_high": 0.2345195759071031
},
{
"model": "Telemetry logistic",
"samples": 8594,
"accuracy": 0.196299744007447,
"balanced_accuracy": 0.2871892331606019,
"macro_f1": 0.1886698746182765,
"weighted_f1": 0.1861407158506876,
"log_loss": 1.5832758165931655,
"brier_score": 0.8215841116420504,
"ece_15_bin": 0.1432688177654283,
"p95_latency_ms": NaN,
"continue_recall": 0.109596713965646,
"continue_f1": 0.1816212871287128,
"slow_recall": 0.601472134595163,
"slow_f1": 0.2506024096385542,
"stop_recall": 0.3706624605678233,
"stop_f1": 0.1760959160734357,
"turn_left_recall": 0.1956782713085234,
"turn_left_f1": 0.1721224920802534,
"turn_right_recall": 0.1585365853658536,
"turn_right_f1": 0.162907268170426,
"macro_f1_route_ci_low": 0.1839562547318565,
"macro_f1_route_ci_high": 0.2044359347158287
},
{
"model": "Majority class",
"samples": 8594,
"accuracy": 0.6232255061670933,
"balanced_accuracy": 0.2,
"macro_f1": 0.1535770609318996,
"weighted_f1": 0.4785657076746885,
"log_loss": 1.1837257781136636,
"brier_score": 0.5768401032344809,
"ece_15_bin": 0.032749657591408,
"p95_latency_ms": NaN,
"continue_recall": 1.0,
"continue_f1": 0.7678853046594982,
"slow_recall": 0.0,
"slow_f1": 0.0,
"stop_recall": 0.0,
"stop_f1": 0.0,
"turn_left_recall": 0.0,
"turn_left_f1": 0.0,
"turn_right_recall": 0.0,
"turn_right_f1": 0.0,
"macro_f1_route_ci_low": 0.1460915032679738,
"macro_f1_route_ci_high": 0.1554760284937855
}
],
"per_class": [
{
"model": "Temporal efficientnet_b0 + telemetry",
"class": "continue",
"precision": 0.759493670886076,
"recall": 0.7393577296489918,
"f1": 0.7492904446546831,
"support": 5356
},
{
"model": "Temporal efficientnet_b0 + telemetry",
"class": "slow",
"precision": 0.40311004784689,
"recall": 0.3543638275499474,
"f1": 0.3771684387241186,
"support": 951
},
{
"model": "Temporal efficientnet_b0 + telemetry",
"class": "stop",
"precision": 0.3754325259515571,
"recall": 0.3422712933753943,
"f1": 0.3580858085808581,
"support": 634
},
{
"model": "Temporal efficientnet_b0 + telemetry",
"class": "turn_left",
"precision": 0.2446511627906976,
"recall": 0.3157262905162065,
"f1": 0.2756813417190775,
"support": 833
},
{
"model": "Temporal efficientnet_b0 + telemetry",
"class": "turn_right",
"precision": 0.1896745230078563,
"recall": 0.2060975609756097,
"f1": 0.1975452951490356,
"support": 820
}
],
"subsets": [
{
"model": "Temporal efficientnet_b0 + telemetry",
"subset": "all_test",
"samples": 8594,
"macro_f1": 0.3915542657655546,
"balanced_accuracy": 0.39156334041323,
"accuracy": 0.5755178031184547
},
{
"model": "Temporal efficientnet_b0 + telemetry",
"subset": "unseen_grid_cells",
"samples": 1846,
"macro_f1": 0.3342824235159851,
"balanced_accuracy": 0.3360174291252364,
"accuracy": 0.5384615384615384
},
{
"model": "Temporal efficientnet_b0 + telemetry",
"subset": "night_utc",
"samples": 6930,
"macro_f1": 0.4102137401798389,
"balanced_accuracy": 0.4080902962744183,
"accuracy": 0.5946608946608947
},
{
"model": "Temporal efficientnet_b0 + telemetry",
"subset": "gps_accuracy_le_10m",
"samples": 8319,
"macro_f1": 0.393316436996118,
"balanced_accuracy": 0.3936744515708604,
"accuracy": 0.5783147012862123
}
],
"selective_prediction": [
{
"confidence_threshold": 0.0,
"coverage": 1.0,
"accepted_examples": 8594,
"selective_accuracy": 0.5755178031184547,
"selective_macro_f1": 0.3915542657655546
},
{
"confidence_threshold": 0.25,
"coverage": 0.9987200372352804,
"accepted_examples": 8583,
"selective_accuracy": 0.5760223698007689,
"selective_macro_f1": 0.3919543899984051
},
{
"confidence_threshold": 0.35,
"coverage": 0.9100535257156156,
"accepted_examples": 7821,
"selective_accuracy": 0.6006904487917146,
"selective_macro_f1": 0.4060706565050537
},
{
"confidence_threshold": 0.45,
"coverage": 0.6947870607400511,
"accepted_examples": 5971,
"selective_accuracy": 0.658348685312343,
"selective_macro_f1": 0.4327252057994619
},
{
"confidence_threshold": 0.55,
"coverage": 0.4717244589248313,
"accepted_examples": 4054,
"selective_accuracy": 0.7323630981746423,
"selective_macro_f1": 0.470227025478709
},
{
"confidence_threshold": 0.65,
"coverage": 0.3019548522224808,
"accepted_examples": 2595,
"selective_accuracy": 0.8092485549132948,
"selective_macro_f1": 0.5275062675719726
},
{
"confidence_threshold": 0.75,
"coverage": 0.1748894577612287,
"accepted_examples": 1503,
"selective_accuracy": 0.8782435129740519,
"selective_macro_f1": 0.5566727737271018
},
{
"confidence_threshold": 0.85,
"coverage": 0.0829648592040958,
"accepted_examples": 713,
"selective_accuracy": 0.938288920056101,
"selective_macro_f1": 0.6097924940442192
}
],
"calibration": {
"method": "temperature scaling",
"temperature": 1.106177568435669,
"fit_split": "validation after restoring the best checkpoint",
"independent_calibration_split": false
},
"limitations": [
"Labels are GPS-derived proxies rather than human safety annotations.",
"The test set contains five held-out routes from one operating domain.",
"Raw accuracy is distorted by the majority continue class; macro F1 is primary.",
"The calibration set is the validation split, not an independent fourth split.",
"This evaluation is not evidence of safe vehicle control."
]
}