{"id":"W2999337514","doi":"10.1111/famp.12513","title":"Benchmarking Community‐Based Couple Therapy: Considering Measurement Reactivity","year":2020,"lang":"en","type":"article","venue":"Family Process","topic":"Attachment and Relationship Dynamics","field":"Psychology","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary; Calgary Laboratory Services","funders":"","keywords":"Benchmarking; Randomized controlled trial; Benchmark (surveying); Psychology; Clinical trial; Clinical psychology; Clinical Practice; Psychotherapist; Medicine; Medical physics; Physical therapy","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.5597447,0.0008880884,0.003529635,0.00483032,0.002929713,0.006093249,0.00363698,0.001981234,0.001984118],"category_scores_gemma":[0.6637588,0.0009884128,0.002499208,0.005610177,0.006665666,0.005309294,0.009503552,0.003073021,0.0002270096],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.004245736,"about_ca_system_score_gemma":0.005480044,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003883565,"about_ca_topic_score_gemma":0.003866802,"domain_scores_codex":[0.2346092,0.7137694,0.02202755,0.007051967,0.02084225,0.001699602],"domain_scores_gemma":[0.3081623,0.5791129,0.04947586,0.03947052,0.02177561,0.002002796],"domain_codex":"methods","domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.005469616,0.001524789,0.2636207,0.01265966,0.01243772,0.0004926096,0.04324853,0.01869761,0.002592476,0.05984713,0.008509267,0.5708999],"study_design_scores_gemma":[0.002586757,0.02127282,0.6159236,0.01453695,0.005613013,0.001655926,0.02615072,0.06625555,0.01038516,0.1546778,0.07984272,0.001098926],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4253434,0.02572768,0.4839979,0.0188471,0.004355228,0.01586046,0.001210156,0.0005200135,0.02413806],"genre_scores_gemma":[0.9332573,0.0009450775,0.05140173,0.003004499,0.0003718863,0.01040916,0.0002333099,0.0001036374,0.0002733182],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5597447,"threshold_uncertainty_score":0.5429133,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2088162784638107,"score_gpt":0.4001709335407262,"score_spread":0.1913546550769155,"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."}}