{"id":"W2949950221","doi":"10.48550/arxiv.1809.05781","title":"Modelling Latent Travel Behaviour Characteristics with Generative Machine Learning","year":2018,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Transportation Planning and Optimization","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Latent variable; Latent variable model; Computer science; Bayesian network; Generative grammar; Machine learning; Artificial intelligence; Generative model; Restricted Boltzmann machine; Mode (computer interface); Latent class model; Graphical model; Preference; Dynamic Bayesian network; Bayesian probability; Artificial neural network; Statistics; Mathematics; Human–computer interaction","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002816758,0.0008733756,0.001178193,0.001560673,0.0004597619,0.0013443,0.002295834,0.001596949,0.002830131],"category_scores_gemma":[0.01268083,0.001011567,0.001876307,0.001524318,0.001610901,0.002140331,0.001473517,0.002242313,0.0005235673],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001645496,"about_ca_system_score_gemma":0.001043365,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009636378,"about_ca_topic_score_gemma":0.01204962,"domain_scores_codex":[0.9984187,0.0009412608,0.00004944237,0.0003094811,0.0001677288,0.0001134777],"domain_scores_gemma":[0.9905469,0.007911363,0.0006186573,0.0005091927,0.0002832015,0.0001307676],"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":[0.00003017871,0.00004079003,0.002534406,0.00004730675,0.00007391172,0.00004723048,0.0001313598,0.9345707,0.000206016,0.05171923,0.0003623914,0.01023642],"study_design_scores_gemma":[0.000003548261,0.000005961387,0.0002259823,0.000006541598,0.000005714025,0.000009293523,0.00001012727,0.9630841,0.00005292263,0.03641747,0.0001721001,0.000006284691],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03179562,0.0001421122,0.9663974,0.0003454457,0.00002138533,0.00004056493,0.000261097,0.0001981525,0.0007982873],"genre_scores_gemma":[0.8343185,0.0003010028,0.1605155,0.0002204121,0.00007099789,0.0003269764,0.000981882,0.0001257847,0.003138948],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.009636378,"threshold_uncertainty_score":0.01916057,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08457697967768811,"score_gpt":0.2080350768243716,"score_spread":0.1234580971466834,"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."}}