{"id":"W4210555285","doi":"10.31234/osf.io/6mdtv","title":"Waiting for Baseline Stability in Single-Case Designs: Is It Worth the Time and Effort?","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Behavioral and Psychological Studies","field":"Psychology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal; Institut universitaire en santé mentale de Montréal; Institut Universitaire en Santé Mentale de Québec","funders":"","keywords":"Baseline (sea); Computer science; Classifier (UML); Stability (learning theory); Type I and type II errors; Machine learning; Empirical research; Support vector machine; Word error rate; Monte Carlo method; Statistical power; Multiple baseline design; Artificial intelligence; Statistics; Psychology; Mathematics","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001446503,0.0003350062,0.0005374022,0.00003718398,0.000165217,0.00009362698,0.0001966909,0.0003875727,0.008880393],"category_scores_gemma":[0.0001288873,0.000203181,0.0001848539,0.0001307424,0.0001817893,0.00002820676,0.0004674528,0.0006158394,0.00003110657],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000318438,"about_ca_system_score_gemma":0.00001644941,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008554591,"about_ca_topic_score_gemma":0.00111456,"domain_scores_codex":[0.9976342,0.000305085,0.0005940308,0.0009329265,0.0001147269,0.000419006],"domain_scores_gemma":[0.998183,0.0009155219,0.0001519954,0.0005648585,0.0001090543,0.000075597],"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":[0.001504768,0.006244585,0.1968104,0.0006476897,0.000862424,0.003064676,0.03661584,0.00002657219,0.0008155745,0.0007845522,0.06285448,0.6897684],"study_design_scores_gemma":[0.02598635,0.006304055,0.6097769,0.003386297,0.004082189,0.004660838,0.1498927,0.01235534,0.003781927,0.03095498,0.1339068,0.0149116],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9829158,0.001784879,0.0008302451,0.006251443,0.0004219818,0.00126654,0.0001484172,0.00006056597,0.006320131],"genre_scores_gemma":[0.9922415,0.00004704918,0.001717987,0.002802592,0.0001676434,0.0004889959,0.00006828138,0.00002362528,0.002442311],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6748568,"threshold_uncertainty_score":0.9920256,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.5246658418997343,"score_gpt":0.3878354918471934,"score_spread":0.1368303500525409,"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."}}