{"id":"W2192978482","doi":"10.1136/ebmed-2015-110342","title":"Improving reporting and utility of evaluations of complex interventions","year":2015,"lang":"en","type":"editorial","venue":"Evidence-Based Medicine","topic":"Health Policy Implementation Science","field":"Health Professions","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Psychological intervention; Computer science; Psychology; Psychiatry","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":["metaresearch"],"domain":"reporting","study_design":"not_applicable","genre":"editorial","about_ca_system":false,"about_ca_topic":false,"confidence":"low","status":"direct model label, unvalidated"},{"model":"gpt","categories":["metaresearch"],"domain":"reporting","study_design":"not_applicable","genre":"editorial","about_ca_system":false,"about_ca_topic":false,"confidence":"high","status":"direct model label, unvalidated"}],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.04277596,0.0002691106,0.001336665,0.0005552843,0.0003937433,0.000004583683,0.0004079558,0.0004379946,0.001848361],"category_scores_gemma":[0.414387,0.0002227613,0.0001347288,0.000746975,0.0008211065,0.0002573806,0.0002182622,0.001144125,0.00001092657],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003307404,"about_ca_system_score_gemma":0.01134928,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007367727,"about_ca_topic_score_gemma":0.0009326228,"domain_scores_codex":[0.9868208,0.002537763,0.006969838,0.0005696237,0.002537245,0.0005647072],"domain_scores_gemma":[0.9479139,0.02933679,0.01514202,0.0009995626,0.00610111,0.0005066073],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00006053454,0.00002333139,0.00409891,0.01022554,0.00001660983,0.000001378436,0.002807248,0.0000017289,0.0004423464,0.00002105361,0.9778857,0.004415597],"study_design_scores_gemma":[0.007135225,0.002408652,0.04151411,0.1041119,0.001037045,0.000002001399,0.01020636,0.004478961,0.0001433252,0.0008899978,0.8274443,0.0006281246],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"editorial","genre_gemma":"editorial","genre_scores_codex":[0.01059058,0.003963198,0.02137721,0.03793737,0.915001,0.006840565,0.001386733,0.0001863978,0.002716933],"genre_scores_gemma":[0.2848098,0.0005323727,0.009915458,0.002747676,0.6980116,0.0008783511,0.0008146471,0.0001187609,0.002171394],"genre_candidate":"editorial","genre_consensus":"editorial","teacher_disagreement_score":0.3716111,"threshold_uncertainty_score":0.9992423,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.8886211946752411,"score_gpt":0.7497801860907314,"score_spread":0.1388410085845098,"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."}}