{"id":"W3163565401","doi":"10.1002/jaba.863","title":"Machine learning to analyze single‐case graphs: A comparison to visual inspection","year":2021,"lang":"en","type":"article","venue":"Journal of Applied Behavior Analysis","topic":"Behavioral and Psychological Studies","field":"Psychology","cited_by":32,"is_retracted":false,"has_abstract":true,"ca_institutions":"St. Lawrence College; Université de Montréal; Institut universitaire en santé mentale de Montréal; Institut Universitaire en Santé Mentale de Québec","funders":"Fonds de Recherche du Québec - Santé","keywords":"Visual inspection; Machine learning; Artificial intelligence; Reliability (semiconductor); Contrast (vision); Computer science; Graph; Word error rate; Statistics; Power (physics); Mathematics; Theoretical computer science","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0004757562,0.0002788501,0.0009995732,0.0009514911,0.0002931228,0.00009584756,0.0001942461,0.0001584937,0.001939132],"category_scores_gemma":[0.00003217885,0.000228383,0.0007204544,0.004347159,0.00004733359,0.00005396069,0.00009614797,0.0006598854,0.0001322843],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001136064,"about_ca_system_score_gemma":0.00001213351,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002210915,"about_ca_topic_score_gemma":0.0005910452,"domain_scores_codex":[0.99749,0.0001553791,0.001035512,0.0004648606,0.0004641171,0.0003901316],"domain_scores_gemma":[0.9984038,0.00007327723,0.0004770323,0.0002531862,0.0003702774,0.0004224187],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00132078,0.008097265,0.7482509,0.000007238125,0.003695634,0.009255191,0.007472006,0.004007377,0.03701906,0.0003435967,0.002278091,0.1782529],"study_design_scores_gemma":[0.00210113,0.003284646,0.9352767,0.0000258631,0.02088958,0.001921069,0.02063356,0.0001389167,0.002871524,0.0001064543,0.011711,0.001039504],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9939398,0.0003325916,0.00278913,0.0003132995,0.0003573333,0.0001457097,0.0000119114,0.00005675448,0.002053512],"genre_scores_gemma":[0.998024,0.00001204193,0.00112577,0.0003411074,0.0001578128,0.00003598637,0.00001420891,0.00002133014,0.0002677681],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1870258,"threshold_uncertainty_score":0.9989733,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1356807519859264,"score_gpt":0.3870588164671596,"score_spread":0.2513780644812331,"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."}}