{"id":"W4390234748","doi":"10.1002/jrsm.1688","title":"Consensus on the definition and assessment of external validity of randomized controlled trials: A <scp>Delphi</scp> study","year":2023,"lang":"en","type":"article","venue":"Research Synthesis Methods","topic":"Delphi Technique in Research","field":"Social Sciences","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"Institute of Infection and Immunity; University of Alberta","funders":"","keywords":"External validity; Delphi method; Internal validity; Systematic review; Delphi; Predictive validity; Criterion validity; Randomized controlled trial; Psychological intervention; Psychology; Management science; Applied psychology; Computer science; Construct validity; Medicine; MEDLINE; Social psychology; Psychometrics; Nursing; Clinical psychology; Artificial intelligence","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":[0.8463758,0.002767468,0.008682255,0.02803396,0.009202933,0.01898717,0.008156858,0.01389767,0.00416193],"category_scores_gemma":[0.8858966,0.004051728,0.01033154,0.01611513,0.02416348,0.02050699,0.02584555,0.0154689,0.001278832],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.02799349,"about_ca_system_score_gemma":0.09349355,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00418257,"about_ca_topic_score_gemma":0.003012078,"domain_scores_codex":[0.06660505,0.7630883,0.1098259,0.006982159,0.05100473,0.002493786],"domain_scores_gemma":[0.04926724,0.800993,0.02425548,0.02589032,0.09657636,0.003017672],"domain_codex":"methods","domain_gemma":"methods","domain_candidate":"methods","domain_consensus":"methods","study_design_codex":"design_other","study_design_gemma":"qualitative","study_design_scores_codex":[0.001353467,0.0003338133,0.006657376,0.1695669,0.005679484,0.0008086525,0.1248981,0.004646226,0.002315825,0.1937512,0.03807222,0.4519168],"study_design_scores_gemma":[0.002047132,0.001157812,0.008598255,0.5280432,0.004405251,0.00171928,0.03921497,0.01556874,0.003854914,0.2345942,0.1596452,0.001151121],"study_design_candidate":"qualitative","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02611115,0.1023409,0.5255766,0.1634435,0.01151668,0.1240022,0.001531071,0.0005879655,0.04488998],"genre_scores_gemma":[0.1965436,0.02768769,0.5859815,0.02610783,0.001601039,0.1596248,0.0008021819,0.000330342,0.001321057],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.1536242,"threshold_uncertainty_score":0.2031079,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.7225730919611445,"score_gpt":0.6545780482241669,"score_spread":0.06799504373697762,"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."}}