{"id":"W4312676180","doi":"10.1145/3510457.3513034","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":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; SQL; Big data; Analytics; SPARK (programming language); Popularity; Scalability; Empirical research; Quality (philosophy); Data science; World Wide Web; Database; 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":[0.01732501,0.0005149436,0.0004199535,0.003355673,0.002891588,0.00367467,0.001296125,0.00140382,0.00153302],"category_scores_gemma":[0.1155204,0.0005643543,0.000379271,0.004463672,0.002974268,0.00726923,0.002119337,0.003042434,0.0004479734],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003267931,"about_ca_system_score_gemma":0.002949417,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01002402,"about_ca_topic_score_gemma":0.01043533,"domain_scores_codex":[0.9844737,0.005045468,0.001503463,0.001376908,0.006242147,0.001358222],"domain_scores_gemma":[0.7729697,0.135716,0.03821276,0.007184607,0.03818101,0.007735957],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.000418561,0.001763507,0.8233047,0.0007470278,0.00008638919,0.0024779,0.09380007,0.0009348879,0.002616832,0.002864735,0.01136368,0.0596217],"study_design_scores_gemma":[0.00004989522,0.001098894,0.7277938,0.0005499265,0.000092938,0.002479601,0.2228434,0.01127775,0.003411006,0.00168645,0.02857143,0.0001447845],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9951298,0.0002485959,0.001046987,0.001116909,0.00001954495,0.0001196203,0.0001752079,0.00005219417,0.002091098],"genre_scores_gemma":[0.9969314,0.000211933,0.001449571,0.0002712717,0.00002299355,0.0000699058,0.0002969494,0.00004269076,0.0007032811],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01732501,"threshold_uncertainty_score":0.0916245,"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."}}