{"id":"W4224235507","doi":"10.31234/osf.io/emabf","title":"Correcting bias in extreme groups design using a missing data approach","year":2022,"lang":"en","type":"preprint","venue":"","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University; University of British Columbia","funders":"","keywords":"Missing data; Computer science; Statistics; Data collection; Variable (mathematics); Power (physics); Data mining; 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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.008298529,0.0003478153,0.0005806934,0.0004117364,0.0002027369,0.0002183701,0.001086473,0.0002587149,0.0002570933],"category_scores_gemma":[0.004425388,0.0003576221,0.00007683547,0.0003371471,0.00003200048,0.0001533457,0.002917654,0.001126507,0.000001692614],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003096857,"about_ca_system_score_gemma":0.0002652658,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001380091,"about_ca_topic_score_gemma":0.00002459365,"domain_scores_codex":[0.9966351,0.0009114246,0.0008010732,0.0008873293,0.0004232465,0.0003418425],"domain_scores_gemma":[0.9952892,0.002301709,0.0004869083,0.001802007,0.00005974413,0.00006044145],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000655518,0.006617691,0.04037156,0.01586383,0.001110865,0.0003254703,0.03806756,0.328388,0.001422054,0.01351578,0.05385303,0.4998087],"study_design_scores_gemma":[0.0001518065,0.00001039116,0.00004985187,0.0004061011,0.00004849867,0.00005622049,0.000906443,0.9121426,0.0002235348,0.08548477,0.00004401431,0.0004757815],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01653856,0.0001269945,0.9786065,0.00002616851,0.0003870212,0.000718807,0.00003177376,0.0008254313,0.002738787],"genre_scores_gemma":[0.07237057,0.000006752738,0.9268445,0.00003445302,0.0000870149,0.0000627041,0.0003449883,0.00008689556,0.0001620711],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.5837546,"threshold_uncertainty_score":0.9998876,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.8907203583539185,"score_gpt":0.4664453053583704,"score_spread":0.4242750529955481,"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."}}