{"id":"W4233143865","doi":"10.31234/osf.io/hwubj","title":"Promises and perils of experimentation: The mutual internal validity problem","year":2020,"lang":"en","type":"preprint","venue":"","topic":"Experimental Behavioral Economics Studies","field":"Social Sciences","cited_by":17,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"External validity; Internal validity; Triangulation; Epistemology; Test (biology); Psychology; Management science; Computer science; Cognitive psychology; Social psychology; Mathematics; Engineering","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":[0.000279808,0.0001556371,0.0002734392,0.00002023916,0.0002707502,0.0001315787,0.0003482247,0.00009298796,0.0003114663],"category_scores_gemma":[0.00003659776,0.0001174022,0.00008822891,0.00003709464,0.0007842508,0.00009756471,0.0009840963,0.000195561,0.000008892875],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000115904,"about_ca_system_score_gemma":0.0001537832,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004547909,"about_ca_topic_score_gemma":0.0007604512,"domain_scores_codex":[0.9988823,0.0001476692,0.0003058058,0.0003171205,0.0001967891,0.0001503116],"domain_scores_gemma":[0.9994386,0.00007522871,0.0002130102,0.0001438843,0.00005684825,0.00007246312],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"qualitative","study_design_scores_codex":[0.000179201,0.0003340799,0.09233066,0.0002457021,0.0003345938,0.000007135054,0.7620644,0.00000921802,0.01232394,0.1179921,0.009686698,0.004492296],"study_design_scores_gemma":[0.001848709,0.0008807975,0.01739543,0.0004392563,0.0003594078,0.000005847068,0.6436669,0.0001415039,0.2488246,0.05282873,0.0315935,0.002015303],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8904101,0.0009145073,0.00003619909,0.004698511,0.0004498954,0.001109144,0.00002924346,0.00006542533,0.102287],"genre_scores_gemma":[0.9963116,0.0004117472,0.001972236,0.0001153224,0.0001931458,0.0001696764,0.000005249401,0.00001060051,0.0008104042],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2365007,"threshold_uncertainty_score":0.6875108,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.159344359733532,"score_gpt":0.4009219403315423,"score_spread":0.2415775805980103,"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."}}