{"id":"W4318185132","doi":"10.1109/bigdata55660.2022.10020719","title":"From Data Warehouse to Lakehouse: A Comparative Review","year":2022,"lang":"en","type":"review","venue":"2022 IEEE International Conference on Big Data (Big Data)","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":65,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"","keywords":"Data warehouse; Computer science; Big data; Data science; Unstructured data; Data management; Data extraction; Analytics; Strengths and weaknesses; Data transformation; Data virtualization; Database; Data mining; Cloud computing","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":["metaresearch","metaepi_narrow","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":["open_science","insufficient_payload"],"category_scores_codex":[0.01202171,0.001083525,0.00336608,0.0009694112,0.0003833817,0.002031271,0.0844325,0.0002023946,0.01805538],"category_scores_gemma":[0.009123594,0.0008831522,0.0002410187,0.001847045,0.0002190458,0.00263279,0.06154928,0.00155858,0.01191348],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003130618,"about_ca_system_score_gemma":0.001485576,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00123872,"about_ca_topic_score_gemma":0.004582827,"domain_scores_codex":[0.9797466,0.002583426,0.003333068,0.006373909,0.007298391,0.0006645376],"domain_scores_gemma":[0.9574002,0.004158267,0.00225961,0.03528107,0.0003933385,0.0005075001],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00002078466,0.0001571821,2.525445e-7,0.0004495791,0.0003278988,0.00006297513,0.00003756451,8.513198e-7,7.606146e-8,0.0007144516,0.5003039,0.4979244],"study_design_scores_gemma":[0.0002660718,0.00007629258,0.000001732904,0.00914134,0.0006437727,0.00001615672,0.0003045546,0.0005753363,1.589689e-7,0.0007503935,0.9872922,0.0009320264],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"review","genre_scores_codex":[2.48294e-7,0.4560863,0.004004519,0.002172947,0.009992622,0.001539545,0.5214807,0.0001009664,0.004622118],"genre_scores_gemma":[0.000002920847,0.6072145,0.0004314948,0.002894839,0.001551814,0.0001746239,0.3853348,0.00005044918,0.00234463],"genre_candidate":"review","genre_consensus":null,"teacher_disagreement_score":0.4969924,"threshold_uncertainty_score":0.9993619,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.9445247924110595,"score_gpt":0.5941263284283097,"score_spread":0.3503984639827498,"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."}}