{"id":"W2799978916","doi":"10.1017/s0033291718001289","title":"Equivalence and non-inferiority testing in psychotherapy research","year":2018,"lang":"en","type":"letter","venue":"Psychological Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":15,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dalhousie University","funders":"","keywords":"Equivalence (formal languages); Content (measure theory); Psychology; Psychotherapist; Information retrieval; Computer science; Mathematics; Discrete 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":[{"model":"gemma","categories":[],"domain":null,"study_design":"not_applicable","genre":"commentary","about_ca_system":false,"about_ca_topic":false,"confidence":"low","status":"direct model label, unvalidated"},{"model":"gpt","categories":[],"domain":null,"study_design":"theoretical_or_conceptual","genre":"commentary","about_ca_system":false,"about_ca_topic":false,"confidence":"medium","status":"direct model label, unvalidated"}],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.2131286,0.0006923329,0.003385734,0.002355861,0.002873487,0.006091176,0.003945834,0.03301637,0.006640222],"category_scores_gemma":[0.5955577,0.0007810129,0.002242382,0.003094007,0.02163701,0.009437591,0.005507218,0.04589412,0.003851033],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.007487289,"about_ca_system_score_gemma":0.007938494,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001184835,"about_ca_topic_score_gemma":0.001525937,"domain_scores_codex":[0.6847129,0.2444091,0.02576415,0.009379894,0.03390804,0.001825788],"domain_scores_gemma":[0.2269604,0.7245443,0.01322156,0.01570029,0.01658349,0.002989983],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.000888882,0.0001066853,0.00285351,0.00280583,0.0002797431,0.00221369,0.001376691,0.0004966256,0.0003366176,0.2216507,0.4993007,0.2676903],"study_design_scores_gemma":[0.0007995508,0.0003639089,0.002542039,0.003983399,0.0001245186,0.004663999,0.0003726679,0.00255256,0.0006167918,0.6663259,0.3175342,0.0001205233],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"commentary","genre_gemma":"commentary","genre_scores_codex":[0.000726748,0.01657321,0.007833915,0.9518708,0.01605588,0.000134992,0.00008620307,0.00004001077,0.006678221],"genre_scores_gemma":[0.04055956,0.01185569,0.01764231,0.8470713,0.07879515,0.001080193,0.00008866264,0.000124103,0.002782986],"genre_candidate":"commentary","genre_consensus":"commentary","teacher_disagreement_score":0.7868714,"threshold_uncertainty_score":0.9703525,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.9178104425000236,"score_gpt":0.7194051522256781,"score_spread":0.1984052902743455,"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."}}