{"id":"W3014193006","doi":"10.1109/tim.2020.2983525","title":"Tracking the Progression of Reading Using Eye-Gaze Point Measurements and Hidden Markov Models","year":2020,"lang":"en","type":"article","venue":"IEEE Transactions on Instrumentation and Measurement","topic":"Gaze Tracking and Assistive Technology","field":"Computer Science","cited_by":27,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Windsor","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Gaze; Eye tracking; Computer science; Scrolling; Computer vision; Artificial intelligence; BitTorrent tracker; Hidden Markov model; Point (geometry); Kalman filter; Reading (process); Line (geometry); Tracking (education)","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":[0.0004686576,0.0001467453,0.0001561621,0.00009903339,0.0002843714,0.0000799588,0.0001804753,0.00005233622,0.000004001115],"category_scores_gemma":[0.000007197084,0.000114226,0.00004280547,0.0002268464,0.0000869828,0.0003734687,0.000006087102,0.0001608667,8.08741e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006273095,"about_ca_system_score_gemma":0.00004363029,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002219412,"about_ca_topic_score_gemma":0.000007763947,"domain_scores_codex":[0.9985659,0.0001014198,0.0002918086,0.0003191143,0.000555486,0.0001662972],"domain_scores_gemma":[0.9994404,0.0000189644,0.0001462477,0.0001710796,0.0001403047,0.00008300656],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00006464689,0.0001300281,0.0004450829,0.00007576278,0.00009770625,0.000001543589,0.00320276,0.001288677,0.1453784,0.0007180531,0.00001507341,0.8485823],"study_design_scores_gemma":[0.002843928,0.0007791735,0.003465629,0.0006528184,0.0001758093,0.00002867336,0.001905948,0.2447998,0.7436987,0.001083043,0.00008110541,0.000485388],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1409081,0.00007805064,0.8559104,0.002401777,0.0001608903,0.0003158519,0.000002710124,0.00009139444,0.0001307973],"genre_scores_gemma":[0.9807002,0.00004224409,0.01897188,0.0002414748,0.0000101757,0.00002165055,3.135643e-7,0.000008920741,0.000003138593],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8480969,"threshold_uncertainty_score":0.4658003,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1236004125379748,"score_gpt":0.3023073997490084,"score_spread":0.1787069872110336,"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."}}