{"id":"W4387946914","doi":"10.48550/arxiv.2310.15057","title":"Shareable Driving Style Learning and Analysis with a Hierarchical Latent Model","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Autonomous Vehicle Technology and Safety","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Institut de Valorisation des Données; National Natural Science Foundation of China","keywords":"Latent Dirichlet allocation; Style (visual arts); Computer science; Driving factors; Mechanism (biology); Dimension (graph theory); Multilevel model; Feature (linguistics); Artificial intelligence; Machine learning; Topic model; China; Mathematics","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002331993,0.0007045074,0.0008052157,0.00106108,0.0004958397,0.0009953433,0.001458009,0.0008940886,0.001937399],"category_scores_gemma":[0.006014034,0.0005237552,0.001750896,0.0009267742,0.0007460791,0.001223327,0.00123389,0.001913016,0.0006951891],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001169881,"about_ca_system_score_gemma":0.0008371286,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01108012,"about_ca_topic_score_gemma":0.01222291,"domain_scores_codex":[0.9987934,0.0005248416,0.00005649994,0.0003647903,0.0001212636,0.0001392324],"domain_scores_gemma":[0.9968189,0.002054489,0.0002769979,0.0004373806,0.0002599662,0.00015223],"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":[0.0006034335,0.0004821682,0.04409915,0.0001594432,0.0004644397,0.0002530877,0.001094416,0.6985245,0.005899417,0.0482797,0.004203521,0.1959367],"study_design_scores_gemma":[0.000007136294,0.00002133186,0.001617067,0.000005408656,0.00001488979,0.00001497779,0.0000192555,0.9891004,0.0001887946,0.008779037,0.0002218614,0.000009962851],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1102428,0.000251475,0.8874368,0.0003050047,0.00002964523,0.0000739221,0.0005168607,0.0003934566,0.0007500236],"genre_scores_gemma":[0.8964012,0.00022059,0.09753685,0.0001399756,0.00007629017,0.0002170364,0.001781271,0.00009177898,0.00353499],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01108012,"threshold_uncertainty_score":0.02203125,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0359647752690461,"score_gpt":0.1668927280088548,"score_spread":0.1309279527398087,"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."}}