{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.2168767,0.00149736,0.002546833,0.006162064,0.004834352,0.01057729,0.006577571,0.004498854,0.002693141],"category_scores_gemma":[0.5215848,0.001536294,0.002838801,0.01075452,0.01825912,0.02676897,0.01065589,0.01103249,0.001713028],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002381751,"about_ca_system_score_gemma":0.005108863,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004315614,"about_ca_topic_score_gemma":0.005271266,"domain_scores_codex":[0.7816876,0.1612647,0.01304733,0.01225447,0.0302074,0.001538576],"domain_scores_gemma":[0.4036559,0.4532046,0.01861242,0.09482268,0.02623684,0.003467538],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.002128021,0.0009374378,0.1352357,0.008351771,0.003128201,0.002877157,0.02347478,0.01753825,0.002828613,0.4213358,0.1073588,0.2748055],"study_design_scores_gemma":[0.0002551513,0.0004280474,0.02672088,0.002695311,0.0002101914,0.001537374,0.01189211,0.0190412,0.00214032,0.8466116,0.08829162,0.0001762103],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1008024,0.02070873,0.5143708,0.3046032,0.008460244,0.004410623,0.01182213,0.001441052,0.03338081],"genre_scores_gemma":[0.4574902,0.007207024,0.4602298,0.04550562,0.009421133,0.00705184,0.008927948,0.0007872689,0.003379147],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7831233,"threshold_uncertainty_score":0.9657305,"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."}}