{"id":"W4409736015","doi":"10.1145/3706598.3714294","title":"GazeNoter: Co-Piloted AR Note-Taking via Gaze Selection of LLM Suggestions to Match Users' Intentions","year":2025,"lang":"en","type":"article","venue":"","topic":"Gaze Tracking and Assistive Technology","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Selection (genetic algorithm); Gaze; Human–computer interaction; Multimedia; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006270434,0.001343103,0.0006729079,0.0007046037,0.0003511301,0.0006400808,0.001010326,0.0009600382,0.02235523],"category_scores_gemma":[0.003874445,0.0004729471,0.000298017,0.000247442,0.0002057914,0.001014797,0.001340801,0.0006187132,0.005668026],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001958018,"about_ca_system_score_gemma":0.0004129016,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004306923,"about_ca_topic_score_gemma":0.008306083,"domain_scores_codex":[0.9994628,0.0001209765,0.00002621401,0.0001579382,0.0001799834,0.00005202381],"domain_scores_gemma":[0.9981487,0.00100375,0.0001116529,0.0002272557,0.0003447327,0.0001640429],"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":[0.005283309,0.0006931376,0.007606557,0.0008805258,0.0001617807,0.0007626208,0.001956882,0.001356534,0.4721287,0.0005012396,0.02820748,0.4804612],"study_design_scores_gemma":[0.00181043,0.007703829,0.129354,0.0004554076,0.0005079533,0.002707234,0.002644713,0.3246749,0.4466758,0.001378773,0.08128365,0.00080332],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.4197865,0.001377198,0.4114043,0.000446656,0.001014738,0.001709946,0.005169827,0.1444618,0.01462902],"genre_scores_gemma":[0.7366672,0.0003016745,0.2358518,0.0003316606,0.0001615165,0.0009867621,0.002552422,0.002442866,0.02070416],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.02235523,"threshold_uncertainty_score":0.07478571,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0153928270299501,"score_gpt":0.3036006606276881,"score_spread":0.2882078335977381,"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."}}