{"id":"W4386797274","doi":"10.23977/jeis.2023.080304","title":"Application Scenarios and Practice of Data Science in the Context of Big Data","year":2023,"lang":"en","type":"article","venue":"Journal of Electronics and Information Science","topic":"Spam and Phishing Detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Big data; Data science; Computer science; Context (archaeology); Domain (mathematical analysis); The Internet; Intersection (aeronautics); Process (computing); Data mining; World Wide Web; Engineering; Mathematics","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.01233619,0.00003947482,0.00008268441,0.0004561499,0.0001483913,0.0002388116,0.002535386,0.00001569875,1.067733e-7],"category_scores_gemma":[0.001674811,0.00002698236,0.000005850294,0.002809612,0.0003267961,0.0232898,0.0005493221,0.0001318551,6.174305e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002478784,"about_ca_system_score_gemma":0.0006596673,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003107971,"about_ca_topic_score_gemma":0.000008159148,"domain_scores_codex":[0.998615,0.00003266685,0.0003932687,0.0001181687,0.0007041085,0.0001368474],"domain_scores_gemma":[0.9979894,0.0002751323,0.0006285433,0.0006182435,0.0004543749,0.00003435179],"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":[0.00004396814,0.00004494806,0.0006271622,0.00003979613,0.00000469457,5.714546e-7,0.00918442,0.0002356616,0.01995908,0.09932569,0.0003338306,0.8702002],"study_design_scores_gemma":[0.0005420564,0.0004645758,0.01887643,0.00005190916,0.00001286295,0.0003220294,0.002873676,0.9191881,0.003275373,0.001671064,0.05261072,0.0001111417],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.569312,0.001309435,0.4127311,0.01288379,0.0008116618,0.0005673012,0.00002703404,0.00002519914,0.002332562],"genre_scores_gemma":[0.9966834,0.00120148,0.001895397,0.0002008588,0.00001546979,4.363827e-7,0.000001867015,6.041217e-7,4.52155e-7],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9189525,"threshold_uncertainty_score":0.9903709,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06016062155716177,"score_gpt":0.3276523948837222,"score_spread":0.2674917733265604,"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."}}