{"id":"W2896121980","doi":"10.5334/ijic.s2085","title":"Too complex to test? Using exploratory trials to identify relevant contexts and mechanisms prior to larger scale evaluations","year":2018,"lang":"en","type":"article","venue":"International Journal of Integrated Care","topic":"Delphi Technique in Research","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University Health Network; Lunenfeld-Tanenbaum Research Institute; McMaster University; University of Toronto","funders":"","keywords":"Scale (ratio); Test (biology); Computer science; Field (mathematics); Data science; Geography","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":["metaresearch"],"category_scores_codex":[0.4402335,0.003510836,0.005136135,0.003176437,0.002961063,0.007259482,0.004329709,0.005823001,0.007576001],"category_scores_gemma":[0.6493174,0.00220275,0.004068601,0.003634247,0.007746768,0.02350021,0.00525459,0.004661734,0.001415455],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00621651,"about_ca_system_score_gemma":0.01790083,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001646875,"about_ca_topic_score_gemma":0.002401493,"domain_scores_codex":[0.4467407,0.4835381,0.03387224,0.01106461,0.02177233,0.003011997],"domain_scores_gemma":[0.2445219,0.6579655,0.03891855,0.036544,0.0190753,0.002974697],"domain_codex":"methods","domain_gemma":"methods","domain_candidate":"methods","domain_consensus":"methods","study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.06398239,0.02689837,0.06729817,0.08126111,0.0180139,0.001298569,0.05302745,0.01149733,0.006641104,0.09354353,0.01412932,0.5624087],"study_design_scores_gemma":[0.1049036,0.2036926,0.06617872,0.07180448,0.01997881,0.001323358,0.05919211,0.04042064,0.01895168,0.3277634,0.08396792,0.001822648],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"protocol","genre_gemma":"methods","genre_scores_codex":[0.3175673,0.01847971,0.2172713,0.01637439,0.003370619,0.4022943,0.001652701,0.0007980626,0.02219169],"genre_scores_gemma":[0.5670635,0.001905422,0.1765031,0.003722572,0.0003297376,0.2493285,0.0003494791,0.00009289772,0.0007048168],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5597665,"threshold_uncertainty_score":0.6902918,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2512322320503015,"score_gpt":0.5494915500989016,"score_spread":0.2982593180486001,"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."}}