{"id":"W4200313442","doi":"10.3389/fnrgo.2021.778043","title":"Eye Tracking in Driver Attention Research—How Gaze Data Interpretations Influence What We Learn","year":2021,"lang":"en","type":"article","venue":"Frontiers in Neuroergonomics","topic":"Human-Automation Interaction and Safety","field":"Psychology","cited_by":55,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; Stiftelsen Länsförsäkringsbolagens Forskningsfond; VINNOVA","keywords":"Gaze; Eye tracking; Tracking (education); Computer science; Psychology; Cognitive psychology; Visual attention; Artificial intelligence; Computer vision; Neuroscience; Cognition","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0006091552,0.0001495415,0.0002347348,0.0005937743,0.0001174176,0.0003866144,0.0005814732,0.0001237873,0.0003802805],"category_scores_gemma":[0.0004941787,0.0001870923,0.0000577282,0.0005608657,0.0001123606,0.002035594,0.0002544544,0.0008928158,0.0001979583],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002540044,"about_ca_system_score_gemma":0.000100774,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003618476,"about_ca_topic_score_gemma":0.000475012,"domain_scores_codex":[0.9974337,0.0008103663,0.0004782217,0.0006968091,0.0001836654,0.0003972214],"domain_scores_gemma":[0.9984733,0.0002204974,0.000126327,0.0009547658,0.0001464366,0.00007869787],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0007795382,0.001313773,0.4822391,0.0001453188,0.0002378252,0.0009193915,0.04163788,0.01329156,0.002718503,0.007644937,0.173194,0.2758781],"study_design_scores_gemma":[0.001752438,0.00006253864,0.7123662,0.0004443259,0.00001724423,0.00003574443,0.03544582,0.05985794,0.00009681493,0.001327419,0.1881562,0.0004372751],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9769197,0.0007208125,0.00649158,0.006210338,0.006744371,0.0002940885,0.00002724636,0.00007544992,0.002516462],"genre_scores_gemma":[0.9925011,0.001303766,0.001696954,0.0005352912,0.00009502742,0.00004170397,0.0001622671,0.00003728834,0.003626549],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2754409,"threshold_uncertainty_score":0.7629404,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08332761163815353,"score_gpt":0.4138333492761461,"score_spread":0.3305057376379925,"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."}}