{"id":"W2912161163","doi":"10.1002/9781119214656.ch11","title":"Description of Datasets","year":2018,"lang":"en","type":"other","venue":"Wiley series in probability and statistics","topic":"Advanced Statistical Methods and Models","field":"Mathematics","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia; Statistics Canada","funders":"","keywords":"Outlier; Multivariate statistics; Computer science; Data mining; Range (aeronautics); Anomaly detection; Artificial intelligence; Machine learning; Engineering","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003190168,0.001236529,0.001169236,0.004979219,0.001156737,0.003758735,0.002610722,0.001565811,0.0833353],"category_scores_gemma":[0.0205475,0.000619579,0.001233183,0.00760271,0.000645084,0.00293936,0.0023381,0.002843749,0.07969807],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001104683,"about_ca_system_score_gemma":0.002374281,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003023589,"about_ca_topic_score_gemma":0.005498904,"domain_scores_codex":[0.996903,0.0007765831,0.0006444267,0.0006309142,0.0008591205,0.0001859645],"domain_scores_gemma":[0.9935422,0.002470932,0.0004531219,0.001718107,0.001484342,0.0003312682],"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":[0.0002271936,0.0001380552,0.002512305,0.001791012,0.00006011499,0.000136586,0.0001658102,0.003378996,0.0009293889,0.007567593,0.9244894,0.05860353],"study_design_scores_gemma":[0.00005462969,0.00004489077,0.001469765,0.0003738677,0.00001772761,0.0001956892,0.0001705115,0.001069399,0.0004754884,0.008424902,0.9876682,0.00003500404],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.002537552,0.002616623,0.01720755,0.001119755,0.0006175917,0.001254009,0.9555283,0.004347296,0.01477117],"genre_scores_gemma":[0.004704323,0.00208991,0.02922704,0.001343823,0.0001475907,0.00430315,0.9490212,0.001165895,0.007997115],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.0833353,"threshold_uncertainty_score":0.2787844,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1009599913770908,"score_gpt":0.3780561449761514,"score_spread":0.2770961535990606,"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."}}