{"id":"W2792845961","doi":"10.1016/j.spl.2018.02.018","title":"Statisticians can do better in the big data era","year":2018,"lang":"en","type":"article","venue":"Statistics & Probability Letters","topic":"Data Analysis with R","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Big data; Compromise; Data science; Computer science; Mathematics; Data mining; Political science; Law","routes":{"ca_aff":true,"ca_fund":true,"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":[0.00176572,0.0002471005,0.0002760706,0.0001381821,0.0002018666,0.0005742222,0.004826103,0.0000453761,0.00003966684],"category_scores_gemma":[0.0006948293,0.0001878203,0.00002893876,0.0008099647,0.0005972065,0.0003878134,0.0009230542,0.0003682449,0.0001267959],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001179047,"about_ca_system_score_gemma":0.0001762825,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008415086,"about_ca_topic_score_gemma":0.006921481,"domain_scores_codex":[0.9965367,0.0005461409,0.0005513077,0.001047842,0.000722412,0.0005956213],"domain_scores_gemma":[0.994598,0.0006988779,0.0001603421,0.004321802,0.000129462,0.00009157029],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00002141032,0.0003571958,0.02839797,0.0001056724,0.0001174706,0.0002694654,0.008746367,0.00001282416,0.0004009174,0.3240866,0.3464768,0.2910073],"study_design_scores_gemma":[0.001003307,0.0002818787,0.1636841,0.00006438782,0.000153626,0.0000372629,0.00006351454,0.03376325,0.0000725462,0.7536975,0.04596332,0.00121529],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01346,0.000008825839,0.9664677,0.0166507,0.0004545914,0.0003826943,0.002346586,0.00005803468,0.0001708428],"genre_scores_gemma":[0.1300066,0.000002851225,0.8469747,0.0220588,0.0003681042,0.00003339825,0.0005273419,0.00001743996,0.00001074143],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4296109,"threshold_uncertainty_score":0.896818,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05480528962070819,"score_gpt":0.2823701365293838,"score_spread":0.2275648469086756,"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."}}