{"id":"W4415302701","doi":"10.1177/01454455251380510","title":"Machine Learning to Detect Vocal Stereotypy: Improving Duration-Based Measures","year":2025,"lang":"en","type":"article","venue":"Behavior Modification","topic":"Behavioral and Psychological Studies","field":"Psychology","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal; Réseau National d'Expertise en Trouble du Spectre de l'Autisme","funders":"Canadian Institutes of Health Research","keywords":"Generalizability theory; Measure (data warehouse); Process (computing); Generalization; Stereotypy; Set (abstract data type); Kappa; Validation test","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":[0.0003164636,0.0001983281,0.0001996793,0.0001687017,0.0003261723,0.00005878376,0.0002170639,0.0001632823,0.0003397027],"category_scores_gemma":[0.00008165941,0.000172211,0.00009096378,0.0004096036,0.00005301907,0.00004974638,0.00003608604,0.0002857137,0.0003027095],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008382538,"about_ca_system_score_gemma":0.00002078344,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006453074,"about_ca_topic_score_gemma":0.0001113576,"domain_scores_codex":[0.9984292,0.0001840794,0.0003929987,0.0005119512,0.0001875808,0.0002941586],"domain_scores_gemma":[0.9992459,0.00007100128,0.0001107476,0.0003585326,0.0001289371,0.00008484534],"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":[0.0002326652,0.0003420508,0.1153691,0.00000918051,0.00001763616,0.000007401054,0.0004150813,0.0000528975,0.03884913,0.0010964,0.0004689585,0.8431395],"study_design_scores_gemma":[0.0006802737,0.0002340067,0.9852957,0.00001715976,0.0001338385,0.000001818053,0.0001936946,0.0001928683,0.002368698,0.00008377763,0.01053235,0.0002658239],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9431371,0.0005514873,0.04912351,0.001315237,0.0009033348,0.0009567126,0.00002326589,0.0003740412,0.00361528],"genre_scores_gemma":[0.9947681,0.000003202553,0.0008259606,0.000379717,0.00005256837,0.0009208798,0.00004766882,0.0000166466,0.002985297],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8699266,"threshold_uncertainty_score":0.7022563,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1925243774694028,"score_gpt":0.367919275826171,"score_spread":0.1753948983567682,"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."}}