{"id":"W4283071214","doi":"10.1109/icse-seip55303.2022.9793914","title":"An Empirical Study on Quality Issues of eBay's Big Data SQL Analytics Platform","year":2022,"lang":"en","type":"article","venue":"","topic":"Cloud Computing and Resource Management","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; SQL; Big data; Analytics; Popularity; World Wide Web; Empirical research; SPARK (programming language); Scalability; Quality (philosophy); Database; Data science; Data mining","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":[0.01639726,0.0004952033,0.0004078631,0.003322633,0.002722515,0.003616257,0.001258849,0.001403795,0.001572641],"category_scores_gemma":[0.1152479,0.0005319212,0.0003679377,0.004226015,0.002798801,0.007391058,0.002083129,0.002860802,0.0004478917],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003165224,"about_ca_system_score_gemma":0.002597579,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009815516,"about_ca_topic_score_gemma":0.01036578,"domain_scores_codex":[0.9849399,0.004995508,0.001446146,0.001289074,0.006045136,0.001284211],"domain_scores_gemma":[0.7791487,0.1308352,0.03872182,0.006855605,0.03663829,0.007800277],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0003925246,0.001813772,0.8250206,0.0006962787,0.00008445772,0.002329219,0.09555817,0.0008852566,0.002431622,0.002669407,0.01092781,0.05719093],"study_design_scores_gemma":[0.00004758334,0.001090654,0.7201714,0.0005357008,0.00008589435,0.002325882,0.2327524,0.01116005,0.003056228,0.00158192,0.02706022,0.0001321737],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9953091,0.0002359499,0.0009391626,0.001116964,0.00001781753,0.0001142263,0.0001610075,0.00004585991,0.002059994],"genre_scores_gemma":[0.9970456,0.0002073019,0.001367274,0.0002646145,0.00002141835,0.00006451735,0.0002817295,0.00003766513,0.0007099728],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01639726,"threshold_uncertainty_score":0.08671808,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2185265045828755,"score_gpt":0.4074982409834229,"score_spread":0.1889717364005474,"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."}}