{"id":"W3129992849","doi":"10.1177/1745691620974773","title":"Promises and Perils of Experimentation: The Mutual-Internal-Validity Problem","year":2021,"lang":"en","type":"article","venue":"Perspectives on Psychological Science","topic":"Decision-Making and Behavioral Economics","field":"Decision Sciences","cited_by":74,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"External validity; Internal validity; Triangulation; Epistemology; Psychology; Test (biology); Cognitive psychology; Social psychology; Management science; Computer science; Mathematics","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":[0.002734917,0.0001237053,0.0002287527,0.0001007829,0.0003495292,0.0004728951,0.0009934393,0.00004493604,0.0008519239],"category_scores_gemma":[0.002818515,0.00006388844,0.0000937535,0.0009500654,0.00190249,0.0003230388,0.0002453842,0.0001529209,0.00007666337],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005884299,"about_ca_system_score_gemma":0.00005741202,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005832286,"about_ca_topic_score_gemma":0.000003319593,"domain_scores_codex":[0.997128,0.0001920805,0.000418945,0.001058738,0.0009756661,0.0002266024],"domain_scores_gemma":[0.9976515,0.0008998274,0.0002158853,0.0006656999,0.0004469929,0.0001200711],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0005269645,0.002905902,0.03050033,0.000003873531,0.00001853772,0.00008172179,0.03601493,0.0000854044,0.09337074,0.05530268,0.004342303,0.7768466],"study_design_scores_gemma":[0.001231115,0.002300624,0.4960413,0.00008183812,0.00002060455,0.0002983326,0.1214702,0.0004546294,0.03846105,0.3308651,0.00815026,0.000624979],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9737905,0.0002438093,0.000316536,0.001961829,0.0003316558,0.0001493033,0.000007060589,0.00001874631,0.02318059],"genre_scores_gemma":[0.9964747,0.00007308037,0.00265845,0.00024918,0.00004221825,0.00001333009,1.601162e-7,0.000003254862,0.0004856073],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7762216,"threshold_uncertainty_score":0.932797,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2525798504219858,"score_gpt":0.5149616096208628,"score_spread":0.262381759198877,"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."}}