{"id":"W2156548034","doi":"10.1016/j.visres.2014.08.014","title":"An inverse Yarbus process: Predicting observers’ task from eye movement patterns","year":2014,"lang":"en","type":"article","venue":"Vision Research","topic":"Gaze Tracking and Assistive Technology","field":"Computer Science","cited_by":89,"is_retracted":false,"has_abstract":false,"ca_institutions":"McGill University Health Centre; McGill University","funders":"","keywords":"Computer science; Artificial intelligence; Hidden Markov model; Eye movement; Task (project management); Inference; Probabilistic logic; Maximum a posteriori estimation; Pattern recognition (psychology); Bayesian inference; Bayesian probability; Process (computing); Computer vision; Machine learning; Mathematics; Maximum likelihood; Statistics","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":[0.001663189,0.0001290558,0.0001528127,0.0002874855,0.0003293121,0.0002593236,0.001726457,0.0001230881,0.00005169752],"category_scores_gemma":[0.0002925165,0.0001119614,0.00003756331,0.0005962828,0.0001090114,0.0004117794,0.0005258317,0.0005485743,0.000161162],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006469188,"about_ca_system_score_gemma":0.00006583593,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006687652,"about_ca_topic_score_gemma":0.0001195582,"domain_scores_codex":[0.9971849,0.0003762538,0.0002185508,0.0007194703,0.0009480602,0.0005528218],"domain_scores_gemma":[0.9982066,0.0002343447,0.00006338007,0.001014584,0.000299041,0.0001820403],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0000317193,0.0007434415,0.6807639,0.00007543766,0.00003969189,0.0000712867,0.002444634,0.0003729562,0.03817412,0.007726155,0.002966436,0.2665902],"study_design_scores_gemma":[0.0008266906,0.001205717,0.4766858,0.0002000885,0.000003816625,7.430615e-7,0.0006923865,0.486371,0.01489674,0.01629262,0.002528604,0.0002957279],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.909205,0.00001413508,0.08805582,0.001585825,0.0001475539,0.0001611886,0.000008806773,0.0003835429,0.000438178],"genre_scores_gemma":[0.994646,0.000008443076,0.004882081,0.0002160356,0.00009406522,0.00003064625,0.00001084756,0.00001294371,0.00009900168],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4859981,"threshold_uncertainty_score":0.4565652,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05068540195553831,"score_gpt":0.3827473229647957,"score_spread":0.3320619210092574,"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."}}