{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.6781713,0.003047319,0.006473075,0.007795068,0.008759686,0.01614907,0.01072628,0.018518,0.007905799],"category_scores_gemma":[0.8039264,0.003232451,0.00497241,0.005102013,0.09510903,0.04948204,0.0211868,0.02640978,0.002039047],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.01365532,"about_ca_system_score_gemma":0.0175103,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002657204,"about_ca_topic_score_gemma":0.001661988,"domain_scores_codex":[0.1998035,0.6574843,0.01858624,0.0272355,0.09401862,0.002871804],"domain_scores_gemma":[0.05961135,0.818987,0.01958282,0.08479906,0.01548347,0.001536413],"domain_codex":"methods","domain_gemma":"methods","domain_candidate":"methods","domain_consensus":"methods","study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0007866376,0.0002869451,0.006273889,0.002626341,0.001227501,0.0002797949,0.008265307,0.002212701,0.0004216038,0.9079185,0.008015278,0.06168548],"study_design_scores_gemma":[0.0004241058,0.0002668224,0.001091116,0.001442357,0.0001693862,0.0002100001,0.0009385218,0.003270779,0.0005123959,0.9723962,0.01915748,0.0001207486],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02471121,0.02967426,0.5085026,0.3022913,0.005776135,0.003821959,0.0007628716,0.0009198001,0.1235397],"genre_scores_gemma":[0.5977074,0.007884448,0.2846147,0.07716691,0.006765155,0.01912292,0.0003731074,0.0006191984,0.005746297],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3218287,"threshold_uncertainty_score":0.3968721,"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."}}