{"id":"W3126143752","doi":"10.1920/wp.cem.2018.4618","title":"Increasing the power of specification tests","year":2018,"lang":"en","type":"preprint","venue":"","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"New York University Abu Dhabi; Frances McClelland Institute for Children, Youth, and Families; York University; Yale University","keywords":"Power (physics); Computer science; Reliability engineering; Engineering; Physics; Thermodynamics","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001041295,0.0001084815,0.0002130392,0.00002601135,0.00003080836,0.00002614312,0.0002707707,0.000113675,0.001447049],"category_scores_gemma":[0.006510514,0.00006154972,0.00005214294,0.0000500866,0.0001475598,0.000009331572,0.0002802404,0.0002040365,0.00002970958],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001737089,"about_ca_system_score_gemma":0.00004554548,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006476596,"about_ca_topic_score_gemma":0.000003710397,"domain_scores_codex":[0.9990146,0.000206332,0.0003311965,0.0001727686,0.0001811198,0.00009403218],"domain_scores_gemma":[0.9958102,0.003062364,0.0002369546,0.0006450139,0.0002184679,0.00002700035],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00001224725,0.0000607225,0.0006087116,0.0001230323,0.00002547369,3.114395e-7,0.0003743146,1.692993e-7,0.0004728772,0.9880792,0.004555672,0.005687195],"study_design_scores_gemma":[0.00003319044,0.0000234392,0.01439796,0.000123644,0.00002687935,0.000002338362,0.00006405376,0.0002543022,0.0013168,0.9833027,0.0003682075,0.00008646628],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1495394,0.00003133554,0.6550918,0.0003179748,0.0003830538,0.0003597965,0.00003382232,0.00005201371,0.1941908],"genre_scores_gemma":[0.4139425,0.000006984251,0.5857422,0.00003009367,0.00007608887,0.000007528008,0.000001667038,0.000009709726,0.000183158],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.2644031,"threshold_uncertainty_score":0.9994658,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1840891769615468,"score_gpt":0.4231925403796681,"score_spread":0.2391033634181213,"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."}}