{"id":"W4409720489","doi":"10.1145/3706599.3721274","title":"Demonstration of GazeNoter: Enhancing AR Note-Taking Through Gaze-Based Selection of LLM Suggestions","year":2025,"lang":"en","type":"article","venue":"","topic":"Gaze Tracking and Assistive Technology","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Gaze; Selection (genetic algorithm); Computer science; Human–computer interaction; Artificial intelligence","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":[0.000197679,0.00009611006,0.0001761495,0.0002237267,0.00007500823,0.00001990326,0.0002939772,0.0001047203,0.00001225315],"category_scores_gemma":[0.0001245298,0.00009366516,0.00006160014,0.0008653521,0.00008019531,0.0001790371,0.000045738,0.0001306566,0.000002899933],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000457008,"about_ca_system_score_gemma":0.0001574928,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001440208,"about_ca_topic_score_gemma":0.0001770187,"domain_scores_codex":[0.9990916,0.00004707098,0.0003304131,0.0002447508,0.0001309912,0.0001551572],"domain_scores_gemma":[0.9991206,0.0001748218,0.0002267751,0.0002698165,0.0001950653,0.00001295091],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000009627367,0.0002474586,0.01150289,0.00008760546,0.00002689963,0.00000110879,0.0001327343,0.002327659,0.415465,0.51111,0.0001689136,0.05892011],"study_design_scores_gemma":[0.0002440658,0.0001235812,0.01924036,0.0001651692,0.00001644361,0.000002362155,0.00002137633,0.04335519,0.930759,0.005872223,0.0001069427,0.00009333707],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05452404,0.00002657445,0.9383322,0.0006721928,0.0001419312,0.00008533108,9.581937e-7,0.0002496736,0.005967083],"genre_scores_gemma":[0.8523531,0.000002477616,0.1474804,0.00006647504,0.000007398884,0.000005767357,0.000001419783,0.000003062347,0.00007989421],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7978291,"threshold_uncertainty_score":0.3819554,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01357158330312882,"score_gpt":0.2836474636422711,"score_spread":0.2700758803391423,"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."}}