{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001772743,0.0001171156,0.0002185021,0.0001343926,0.0002364345,0.00008545133,0.003223589,0.00001607639,0.00002804044],"category_scores_gemma":[0.00003008572,0.00009462107,0.0000412292,0.0005858416,0.00002680505,0.00003073776,0.004080423,0.0001753724,0.000008203003],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004124254,"about_ca_system_score_gemma":0.00003268908,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004047755,"about_ca_topic_score_gemma":0.0000474273,"domain_scores_codex":[0.9978259,0.0002202016,0.000357838,0.0005882789,0.0008031743,0.0002046533],"domain_scores_gemma":[0.9969434,0.0001228136,0.0001170725,0.002712189,0.00003148497,0.00007304703],"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":[0.0001426196,0.02186559,0.2856743,0.00008282138,0.0006069455,0.0001790558,0.03217471,0.1474197,0.00008296547,0.03322874,0.05895537,0.4195872],"study_design_scores_gemma":[0.0007443338,0.00248059,0.1003162,0.000005277014,0.000025673,0.000003130368,0.00994478,0.858376,0.00005488105,0.0007941836,0.02690588,0.0003490221],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.965378,0.00001849827,0.02900176,0.001390759,0.0003574068,0.0002071806,0.000008424925,0.0001873731,0.003450554],"genre_scores_gemma":[0.9966255,3.769074e-7,0.001888868,0.0004733794,0.0001004862,0.000003325019,0.000008029013,0.00000594258,0.0008940613],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7109563,"threshold_uncertainty_score":0.5990283,"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."}}