{"id":"W2782619198","doi":"10.1109/bigdata.2017.8257934","title":"Sanzu: A data science benchmark","year":2017,"lang":"en","type":"article","venue":"","topic":"Data Visualization and Analytics","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of New Brunswick","funders":"","keywords":"Computer science; Benchmark (surveying); Scalability; Python (programming language); Analytics; Data analysis; Data mining; Macro; Big data; Data modeling; Data science; Machine learning; Database; Operating system","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":[0.006788549,0.002380323,0.00103813,0.003824847,0.0015057,0.003459813,0.004761482,0.001449592,0.00588775],"category_scores_gemma":[0.02597673,0.0008347733,0.001488744,0.007824876,0.001336206,0.00430976,0.002949822,0.002281044,0.003310127],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0027572,"about_ca_system_score_gemma":0.004023157,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01529562,"about_ca_topic_score_gemma":0.01419296,"domain_scores_codex":[0.9898174,0.002222719,0.001145198,0.001657923,0.004392216,0.000764454],"domain_scores_gemma":[0.9830646,0.005159684,0.0008698602,0.00376968,0.006226609,0.0009096204],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.002521557,0.001733338,0.02284705,0.00448325,0.0006813752,0.0004591306,0.0004993869,0.1258161,0.01246202,0.02589301,0.6620407,0.1405631],"study_design_scores_gemma":[0.001479442,0.001545077,0.02904125,0.0006124449,0.0002887152,0.0005887414,0.0007383199,0.481114,0.03644737,0.03990672,0.4079778,0.0002600203],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.3417972,0.01053937,0.09991122,0.007267628,0.002534379,0.002580289,0.2585061,0.1774236,0.09944019],"genre_scores_gemma":[0.3368132,0.001991099,0.1638241,0.001786645,0.0002382083,0.001970618,0.4757324,0.009222304,0.00842153],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.01529562,"threshold_uncertainty_score":0.03590173,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1043691251512838,"score_gpt":0.3999943821222473,"score_spread":0.2956252569709635,"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."}}