{"id":"W2990831234","doi":"10.1109/jproc.2019.2952735","title":"Learning Driving Models From Parallel End-to-End Driving Data Set","year":2019,"lang":"en","type":"article","venue":"Proceedings of the IEEE","topic":"Autonomous Vehicle Technology and Safety","field":"Engineering","cited_by":51,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"National Key Research and Development Program of China; National Natural Science Foundation of China","keywords":"Real world data; End-to-end principle; Computer science; Heading (navigation); Data set; Global Positioning System; Set (abstract data type); Artificial intelligence; Computer vision; Engineering; Data science","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003133266,0.0001906775,0.0002755272,0.00007907287,0.0001052004,0.00003357564,0.001427457,0.0001715536,0.00005905967],"category_scores_gemma":[0.00006606949,0.0001652517,0.00005765603,0.0002064769,0.00004872037,0.0005188054,0.0005447827,0.0005584794,0.00007707538],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005202017,"about_ca_system_score_gemma":0.00001513011,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003932197,"about_ca_topic_score_gemma":0.00001208256,"domain_scores_codex":[0.9988331,0.000004464328,0.0002784587,0.00034327,0.000203627,0.0003371052],"domain_scores_gemma":[0.9993302,0.00007281709,0.00009847773,0.0003967031,0.00004611689,0.00005573161],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003607717,0.0000488695,0.1885265,0.0002479597,0.0004474244,0.0000016938,0.005071047,0.4031863,0.3753845,0.004202834,0.006082302,0.01676445],"study_design_scores_gemma":[0.0004072149,0.0000478878,0.01253769,0.0003067431,0.00006506575,0.000007707924,0.0007785992,0.9392708,0.03670784,0.006123744,0.003260124,0.0004865949],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9915503,0.00007062825,0.001583853,0.0002733788,0.0003000572,0.000225028,0.0000172402,0.0005231432,0.005456329],"genre_scores_gemma":[0.995902,0.00003325473,0.003508762,0.00003464128,0.00007311851,0.000008853748,0.000006227588,0.00004857296,0.0003845383],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5360845,"threshold_uncertainty_score":0.6738768,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01762986572833407,"score_gpt":0.216986778027467,"score_spread":0.1993569122991329,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}