{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005757069,0.0001656709,0.0001863485,0.00004418585,0.0003575458,0.00003749238,0.0002256431,0.0001185241,0.0001104851],"category_scores_gemma":[0.000046451,0.0001551537,0.00005759441,0.0002445068,0.00006982215,0.00009979302,0.0000325233,0.0005991652,0.0000639127],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005558209,"about_ca_system_score_gemma":0.00009231171,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009851487,"about_ca_topic_score_gemma":0.00001848751,"domain_scores_codex":[0.998762,0.0002295751,0.0002146183,0.0002210105,0.0003280506,0.0002447328],"domain_scores_gemma":[0.9992228,0.000152875,0.0001252611,0.0002629811,0.0001375903,0.0000985662],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.001138048,0.001955104,0.8484123,0.0006083032,0.0007041243,0.00006593029,0.06465841,0.005627917,0.02507776,0.002178506,0.006009891,0.04356365],"study_design_scores_gemma":[0.01360542,0.001950076,0.7910506,0.0004843492,0.0002852935,0.00001610359,0.03536058,0.08386303,0.005082984,0.003411279,0.06200176,0.002888545],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9587338,0.0005410335,0.01411281,0.00103865,0.000389623,0.0003837137,0.000008729075,0.0002417297,0.02454992],"genre_scores_gemma":[0.9965443,0.000007788576,0.0002475494,0.002944359,0.0001149051,0.00005236364,0.00003112547,0.0000273849,0.00003021428],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.07823511,"threshold_uncertainty_score":0.6326982,"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."}}