{"id":"W2955224228","doi":"10.48550/arxiv.1906.11211","title":"Predicting Confusion from Eye-Tracking Data with Recurrent Neural Networks","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Retinal Imaging and Analysis","field":"Medicine","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Classifier (UML); Artificial intelligence; Recurrent neural network; Confusion; Visualization; Deep learning; Eye tracking; Random forest; Machine learning; Raw data; Artificial neural network; Feature (linguistics); Feature learning; Deep neural networks; Feature engineering; Pattern recognition (psychology)","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":[0.002589095,0.001264342,0.0007376215,0.001995926,0.0002821161,0.001035428,0.0006415041,0.0009924779,0.000752949],"category_scores_gemma":[0.01855944,0.0002541804,0.000611322,0.0008855572,0.0003719353,0.001127274,0.001149348,0.001176647,0.0005245501],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008619053,"about_ca_system_score_gemma":0.0004995105,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007806804,"about_ca_topic_score_gemma":0.009313175,"domain_scores_codex":[0.9986084,0.000420017,0.0001145313,0.0003750929,0.0003017466,0.0001801844],"domain_scores_gemma":[0.9911562,0.005733429,0.0009962493,0.0005767979,0.001301322,0.0002359382],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.002870307,0.0009062476,0.2182837,0.0004830511,0.0006349024,0.0009381398,0.001031569,0.1688009,0.06428664,0.001627343,0.0103542,0.529783],"study_design_scores_gemma":[0.00001954581,0.0002406216,0.03973415,0.00003946657,0.00004336176,0.000254452,0.00008741925,0.9359186,0.02122844,0.001712282,0.0006723656,0.00004931586],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9112635,0.0009616624,0.08181958,0.0004323769,0.0001497478,0.00009600144,0.001740606,0.002192237,0.001344325],"genre_scores_gemma":[0.974399,0.0001333877,0.02322478,0.0000695067,0.00004021504,0.00003009171,0.001339926,0.0000405085,0.0007225035],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.007806804,"threshold_uncertainty_score":0.01552272,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08441188293787544,"score_gpt":0.2406712080352702,"score_spread":0.1562593250973948,"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."}}