{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.5963983,0.0001880879,0.003202303,0.001071328,0.000648444,0.0001595355,0.0007801998,0.0001790368,0.000133592],"category_scores_gemma":[0.6637228,0.0001103732,0.0006685631,0.001604115,0.002475991,0.00005521434,0.0003205572,0.0007329299,0.000006943883],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001344084,"about_ca_system_score_gemma":0.0008083713,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001682664,"about_ca_topic_score_gemma":0.00006255809,"domain_scores_codex":[0.6499667,0.3403398,0.002401896,0.0006271439,0.005644881,0.001019602],"domain_scores_gemma":[0.3401652,0.6571873,0.0006968257,0.0005890068,0.001181569,0.0001801594],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.06430057,0.005258334,0.006164998,0.0006591148,0.005047288,0.0001770384,0.03568409,0.00005232343,0.1329315,0.5824832,0.01569712,0.1515444],"study_design_scores_gemma":[0.178174,0.00226554,0.01195115,0.001585438,0.001406659,0.00000498151,0.2275046,0.0125433,0.1169805,0.4450057,0.002151132,0.0004270245],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9157476,0.0003628863,0.008039392,0.006450229,0.0002102199,0.01617294,0.00005710154,0.0001801174,0.05277953],"genre_scores_gemma":[0.9574451,0.00154721,0.03731417,0.000008912056,0.0001098369,0.003191305,5.630319e-7,0.00002516071,0.0003577629],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3168475,"threshold_uncertainty_score":0.9122893,"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."}}