{"id":"W2564142045","doi":"10.1109/btas.2016.7791194","title":"Pitfalls in studying “big data” from operational scenarios","year":2016,"lang":"en","type":"article","venue":"","topic":"Biometric Identification and Security","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Institute of Standards and Technology; International Research and Exchanges Board","keywords":"Computer science; Big data; Data science; Risk analysis (engineering); Data mining; Medicine","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003718605,0.00005290184,0.00006742554,0.0001753871,0.00004850064,0.0001721988,0.001238871,0.00003099243,0.0002099728],"category_scores_gemma":[0.0001153699,0.00003447246,0.00001071273,0.0005463535,0.00001844692,0.0006558335,0.0004914489,0.00004012724,0.0005186802],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003171421,"about_ca_system_score_gemma":0.00007145236,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004318776,"about_ca_topic_score_gemma":0.0004735552,"domain_scores_codex":[0.999053,0.00004948673,0.0001768969,0.0003712207,0.0002351888,0.000114213],"domain_scores_gemma":[0.9989812,0.0001324359,0.00002661306,0.0007700695,0.00004514278,0.00004453643],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.000006967813,0.0006413783,0.0612009,0.000004377933,0.00003439693,0.00001933354,0.00121082,0.000004064163,0.01537987,0.1602292,0.04447721,0.7167915],"study_design_scores_gemma":[0.002892484,0.00004018015,0.6572232,0.00005365576,0.000005231074,0.000004992918,0.0001227473,0.09031326,0.00474179,0.008741925,0.2351639,0.0006965459],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05417328,0.00007064267,0.9371183,0.006150059,0.0006961012,0.000110813,0.00002922395,0.00008026927,0.001571306],"genre_scores_gemma":[0.981811,0.00001505416,0.01622976,0.0006142405,0.00008116705,0.000003830512,0.00001997216,0.000002164175,0.00122279],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9276378,"threshold_uncertainty_score":0.6666757,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.149973074362681,"score_gpt":0.2976117668679559,"score_spread":0.1476386925052749,"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."}}