{"id":"W3208502467","doi":"10.17605/osf.io/znvwb","title":"Generating accurate 3D gaze vectors using synchronized eye tracking and motion capture","year":2021,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Gaze Tracking and Assistive Technology","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer vision; Computer science; Artificial intelligence; Gaze; Monocular; Eye tracking","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":[0.0007806323,0.00266358,0.0008565611,0.001637193,0.0006438525,0.0009205706,0.001735696,0.0008672556,0.09680831],"category_scores_gemma":[0.004097765,0.001126284,0.000880892,0.001134654,0.0003032474,0.000793455,0.0012662,0.0008749944,0.03564228],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004904537,"about_ca_system_score_gemma":0.001113388,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003275633,"about_ca_topic_score_gemma":0.004345469,"domain_scores_codex":[0.99958,0.00003883327,0.0000417597,0.00010191,0.0001760868,0.00006149365],"domain_scores_gemma":[0.9986542,0.0005218087,0.0001009226,0.0002544172,0.0004112279,0.00005737359],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001068918,0.0002384172,0.004152808,0.0009775423,0.0002086642,0.00095681,0.0005219103,0.01832405,0.076644,0.006631138,0.6405737,0.249702],"study_design_scores_gemma":[0.0008901859,0.0002629178,0.01604985,0.0002199597,0.0001537406,0.001125544,0.0002048328,0.3557884,0.4074728,0.01116286,0.2063269,0.0003421306],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.008498829,0.00005050582,0.5601041,0.0001740978,0.0001915206,0.0004416943,0.07721104,0.34828,0.005048174],"genre_scores_gemma":[0.07714674,0.0002660566,0.65822,0.0002916606,0.0001116568,0.004175631,0.1529556,0.08584952,0.02098305],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.09680831,"threshold_uncertainty_score":0.3238561,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02015615444794315,"score_gpt":0.2439643866135396,"score_spread":0.2238082321655965,"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."}}