{"id":"W4414758275","doi":"10.1109/tvcg.2025.3616811","title":"Seeing What Matters: Attentional (MIS-) Alignment between Humans and AI in VR-Simulated Prediction of Driving Accidents","year":2025,"lang":"en","type":"article","venue":"IEEE Transactions on Visualization and Computer Graphics","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"Department of Artificial Intelligence, Korea University; National Research Foundation of Korea; Korea University; Ministry of Science and ICT, South Korea; Indian Institute of Technology, Patna","keywords":"Focus (optics); Point (geometry); Event (particle physics); Path (computing); Key (lock); Virtual reality; Time point; Accident (philosophy)","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001987456,0.000468112,0.0003239716,0.0004015271,0.0002746222,0.001260431,0.0006182483,0.0006120927,0.001108887],"category_scores_gemma":[0.02011696,0.000370226,0.0003592685,0.0002345465,0.0005228203,0.001648827,0.00141555,0.0008271825,0.0001856565],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000686629,"about_ca_system_score_gemma":0.0005704135,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01522177,"about_ca_topic_score_gemma":0.009871459,"domain_scores_codex":[0.9986542,0.0005217564,0.00006511307,0.000435778,0.0001709823,0.0001521622],"domain_scores_gemma":[0.9955698,0.002849257,0.0005134583,0.0004814432,0.0002989865,0.0002871921],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.004596233,0.001116006,0.3528578,0.0004002822,0.0006154056,0.0005321731,0.01182141,0.1731677,0.129092,0.003479001,0.00246801,0.3198539],"study_design_scores_gemma":[0.0001186151,0.001570254,0.3549092,0.00007758991,0.0002509418,0.0003859152,0.002957796,0.6132994,0.01636077,0.00790048,0.002012624,0.0001564693],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9855306,0.0002045848,0.01205918,0.0001918514,0.00003064147,0.0000251273,0.00004637591,0.0001176828,0.001793861],"genre_scores_gemma":[0.9978131,0.00003451218,0.001864972,0.000050549,0.000005587785,0.000008790544,0.00003821637,0.00001102313,0.0001731573],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01522177,"threshold_uncertainty_score":0.03026634,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0222461440174426,"score_gpt":0.3014032026101051,"score_spread":0.2791570585926625,"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."}}