{"id":"W4225106913","doi":"10.1002/jaba.921","title":"Agreement between visual inspection and objective analysis methods: A replication and extension","year":2022,"lang":"en","type":"article","venue":"Journal of Applied Behavior Analysis","topic":"Behavioral and Psychological Studies","field":"Psychology","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"Fonds de Recherche du Québec - Santé","keywords":"Visual inspection; Inter-rater reliability; Replicate; Classifier (UML); Support vector machine; Replication (statistics); Artificial intelligence; Psychology; Machine learning; Pattern recognition (psychology); Extension (predicate logic); Computer science; Statistics; Mathematics; Developmental psychology; Rating scale","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"observational","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"high","status":"direct model label, unvalidated"},{"model":"gpt","categories":[],"domain":null,"study_design":"observational","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"low","status":"direct model label, unvalidated"}],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001723877,0.0001872875,0.0008431291,0.001058903,0.0004660017,0.00003693171,0.0001317351,0.00008594145,0.0007128561],"category_scores_gemma":[0.00001338358,0.0001510571,0.0004036227,0.002794073,0.000105866,0.00005656595,0.0001521975,0.0004383684,0.000002430914],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001168981,"about_ca_system_score_gemma":0.000007110942,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002018645,"about_ca_topic_score_gemma":0.0000270615,"domain_scores_codex":[0.9978316,0.0003122243,0.0007173873,0.0005496627,0.0003904361,0.0001987245],"domain_scores_gemma":[0.9985079,0.0001302494,0.0007678954,0.0003190936,0.0001424394,0.0001324107],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0004174422,0.0008729381,0.71793,0.000002724366,0.007605385,0.00003265803,0.003411593,0.0001031755,0.005171526,0.0001668605,0.0001493593,0.2641363],"study_design_scores_gemma":[0.0004850652,0.0005209271,0.9611481,9.222743e-7,0.03243992,0.00001960271,0.004541364,0.000043246,0.0001106082,0.0001991289,0.0003282905,0.0001627934],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9924687,0.0005080097,0.006089163,0.0001435945,0.00009012085,0.0001999069,0.00001902327,0.00002219159,0.0004593234],"genre_scores_gemma":[0.997806,0.00006235966,0.001759147,0.00008042305,0.0000810382,0.0001071839,0.00002161121,0.000009037904,0.00007326755],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2639736,"threshold_uncertainty_score":0.7805274,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.136103726726318,"score_gpt":0.4345176438425861,"score_spread":0.298413917116268,"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."}}