{"id":"W3191733181","doi":"10.1214/21-aoas1501","title":"The ASA president’s task force statement on statistical significance and replicability","year":2021,"lang":"en","type":"article","venue":"The Annals of Applied Statistics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":41,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Task force; Statement (logic); Task (project management); Statistical analysis; Statistics; Computer science; Econometrics; Natural language processing; Mathematics; Political science; Law; Management; Economics","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":[],"category_scores_codex":[0.00665404,0.0002911123,0.0007043376,0.00002070479,0.0003717293,0.000111555,0.0004664016,0.0001051578,0.0001442966],"category_scores_gemma":[0.05931144,0.0001773197,0.00007224241,0.0001888588,0.001137249,0.00002358842,0.0002846397,0.0004574249,0.00001908618],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002943506,"about_ca_system_score_gemma":0.0001794265,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001599774,"about_ca_topic_score_gemma":0.0000253112,"domain_scores_codex":[0.9953939,0.0009812603,0.001585526,0.000621802,0.0008864367,0.0005310831],"domain_scores_gemma":[0.8735695,0.1239185,0.0005614384,0.001356998,0.0004141421,0.000179473],"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":[0.0006102726,0.0002042394,0.00001491223,0.0001843501,0.0001376023,0.00001253005,0.0002407169,0.00001912398,0.0004680371,0.9313173,0.0388591,0.02793179],"study_design_scores_gemma":[0.0004638285,0.0002302706,0.001610665,0.00003591525,0.0001092518,0.000002043827,0.0003857612,0.0004401128,0.008744556,0.9844792,0.003301378,0.0001970452],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01135682,0.0001752924,0.9679732,0.005667308,0.0003797172,0.001943719,0.005576773,0.00008641865,0.006840729],"genre_scores_gemma":[0.1861091,0.0009365461,0.8101794,0.001490584,0.0001946559,0.0002388644,0.00002425157,0.0000757114,0.0007508836],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.1747523,"threshold_uncertainty_score":0.9486124,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.5158428041741353,"score_gpt":0.5546070747217429,"score_spread":0.03876427054760756,"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."}}