{"id":"W4394142622","doi":"10.6084/m9.figshare.22575157.v1","title":"What is a randomization test?","year":2023,"lang":"en","type":"dataset","venue":"Figshare","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Randomization; Test (biology); Restricted randomization; Computer science; Psychology; Medicine; Randomized controlled trial; Biology; Internal medicine","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","metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0007762161,0.0003228315,0.001017571,0.0001106184,0.00006394392,0.0002969866,0.0006006764,0.0007494123,0.342107],"category_scores_gemma":[0.7304423,0.0002950857,0.0002764807,0.0003379951,0.00001269774,0.0001188674,0.000347632,0.0005746034,0.08701602],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004705165,"about_ca_system_score_gemma":0.0001002594,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004098327,"about_ca_topic_score_gemma":0.000006878864,"domain_scores_codex":[0.9972277,0.0004483628,0.0009246216,0.0005365526,0.0005543614,0.0003084284],"domain_scores_gemma":[0.7780526,0.2199726,0.0005987267,0.001015314,0.0002190151,0.0001416586],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00003116021,0.00005545748,1.461679e-8,0.001395225,0.00005174963,0.00003560351,0.000006117461,1.037e-7,6.530978e-8,0.000006188796,0.9966778,0.001740507],"study_design_scores_gemma":[0.001330797,0.00003792141,0.000001032041,0.008100345,0.0001209947,0.000001696941,0.000005620743,0.00002002855,0.00001011453,0.1697728,0.8203195,0.0002791775],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[6.031012e-9,0.00007814112,0.00001836757,0.0001580316,0.00121404,0.0009058101,0.997398,0.0001850809,0.00004254131],"genre_scores_gemma":[2.524459e-9,0.0002424256,0.01772332,0.0006311939,0.001029002,0.0006902746,0.9787004,0.00007664198,0.0009067406],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.7296662,"threshold_uncertainty_score":0.9999501,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.67800825717898,"score_gpt":0.5872659920947213,"score_spread":0.09074226508425864,"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."}}