{"id":"W3135120323","doi":"10.1080/23249935.2021.1898487","title":"Microscopic modeling of cyclists interactions with pedestrians in shared spaces: a Gaussian process inverse reinforcement learning approach","year":2021,"lang":"en","type":"article","venue":"Transportmetrica A Transport Science","topic":"Traffic and Road Safety","field":"Engineering","cited_by":37,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Reinforcement learning; Process (computing); Machine learning; Artificial intelligence; Microsimulation; Gaussian process; Human–computer interaction; Pedestrian; Gaussian; Engineering; Transport engineering","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":[0.0002804984,0.0002665932,0.0004147018,0.0007535214,0.0001489082,0.00002977532,0.0003570664,0.00007452865,0.00005502488],"category_scores_gemma":[0.00001283148,0.0002433695,0.00009361187,0.005654621,0.0002327749,0.0006219917,0.000005191345,0.000463591,0.000002028648],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001268585,"about_ca_system_score_gemma":0.0004535187,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00011831,"about_ca_topic_score_gemma":0.0005123563,"domain_scores_codex":[0.9977086,0.00001254258,0.0006132258,0.0005235702,0.0005947815,0.0005472846],"domain_scores_gemma":[0.999275,0.00002134417,0.00007483195,0.000288979,0.0001433983,0.0001964394],"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":[0.00004123687,0.0001211787,0.03670764,0.0003230114,0.00002094826,0.00006825066,0.005172003,0.9550543,0.002228686,0.0000646188,7.46327e-7,0.0001973179],"study_design_scores_gemma":[0.001795484,0.00009402855,0.07225082,0.0004831007,0.0001007179,0.00004279865,0.00360246,0.9171326,0.003754511,0.000009643736,0.0001392254,0.0005946458],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8199383,0.000119175,0.1731445,0.00002741665,0.00008570591,0.0002796744,0.00001445314,0.000185979,0.00620477],"genre_scores_gemma":[0.9933056,0.0001227895,0.006310977,0.000009587176,0.0000122962,0.00003649341,0.00007425244,0.00003226745,0.00009577283],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1733672,"threshold_uncertainty_score":0.9924322,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01824803005132324,"score_gpt":0.2412460335899745,"score_spread":0.2229980035386513,"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."}}