{"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":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.0005351331,0.00004637408,0.00005066737,0.00005566742,0.000703798,0.001799009,0.00956354,0.00001080906,0.0000856597],"category_scores_gemma":[0.0003460202,0.00003720001,0.000008201369,0.0001618536,0.0002250144,0.004641813,0.004014561,0.00002984192,0.0001700004],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000008036112,"about_ca_system_score_gemma":0.0001452743,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003829911,"about_ca_topic_score_gemma":0.00001750652,"domain_scores_codex":[0.9990951,0.000005668012,0.00008321978,0.0003698552,0.0002885778,0.0001575439],"domain_scores_gemma":[0.9955685,0.00001090384,0.00006332749,0.004201011,0.0000650025,0.00009128742],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[1.75625e-7,0.00002337753,0.001382148,0.000001879193,0.000001994149,0.000003897369,0.00003486091,0.000001152749,0.0002218184,0.9473734,0.02608108,0.02487421],"study_design_scores_gemma":[0.0001438352,0.00001293412,0.01224894,0.000008132341,0.000002453784,0.000005504528,0.00001260127,0.8313968,0.000900224,0.002621431,0.1524935,0.0001535942],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0003616427,0.000008015993,0.8164166,0.001916537,0.0003212603,0.00003452187,0.00001000792,0.0000878923,0.1808436],"genre_scores_gemma":[0.9119508,0.00002583409,0.08310133,0.00137084,0.00006962125,6.200432e-7,0.00002281194,0.000003279702,0.003454874],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.944752,"threshold_uncertainty_score":0.9992372,"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."}}