{"id":"W4410701915","doi":"10.1145/3715669.3726785","title":"Learning Disorder Detection Using Eye Tracking: Are Large Language Models Better Than Machine Learning?","year":2025,"lang":"en","type":"article","venue":"","topic":"Gaze Tracking and Assistive Technology","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"ca_institutions":"Mila - Quebec Artificial Intelligence Institute","funders":"","keywords":"Computer science; Artificial intelligence; Eye tracking; Machine learning; Tracking (education); Natural language processing; 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":[0.00638087,0.001905634,0.002283143,0.001229284,0.0005954105,0.003805913,0.001642142,0.002572249,0.003543778],"category_scores_gemma":[0.03708785,0.0006954058,0.001455821,0.0009337185,0.0007909103,0.009941899,0.001146869,0.002553306,0.00310693],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007116944,"about_ca_system_score_gemma":0.001137378,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008958176,"about_ca_topic_score_gemma":0.008249468,"domain_scores_codex":[0.9972818,0.001212986,0.0001760101,0.0008454135,0.0002721116,0.0002116107],"domain_scores_gemma":[0.9833378,0.0117053,0.0009316729,0.002050283,0.001511962,0.0004630332],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.002227143,0.001177193,0.1486881,0.0005812162,0.001637701,0.0002408937,0.0003648024,0.04918627,0.009777377,0.004218564,0.02481888,0.7570819],"study_design_scores_gemma":[0.0001503052,0.0005935628,0.03086158,0.0002110067,0.0004703311,0.0003496551,0.0003747592,0.9241739,0.005325296,0.03385115,0.003519672,0.0001188147],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5008572,0.02256979,0.4241515,0.02565169,0.001970274,0.0002816115,0.005799714,0.007638699,0.01107953],"genre_scores_gemma":[0.9408258,0.002789945,0.04905878,0.001490804,0.0006483867,0.00007489972,0.002196382,0.0003485867,0.002566437],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.008958176,"threshold_uncertainty_score":0.03374565,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01232598692517258,"score_gpt":0.2681987318658679,"score_spread":0.2558727449406953,"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."}}