{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004710013,0.0008632672,0.001620962,0.008820729,0.000556712,0.002913747,0.002102344,0.001376379,0.003942612],"category_scores_gemma":[0.007918675,0.0007103677,0.001130129,0.01868758,0.001201794,0.005366818,0.001491017,0.001742148,0.001646591],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00184064,"about_ca_system_score_gemma":0.004729199,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004187888,"about_ca_topic_score_gemma":0.006539751,"domain_scores_codex":[0.9984487,0.0003991753,0.0002980063,0.0002031419,0.0005606585,0.00009023998],"domain_scores_gemma":[0.9920392,0.005211985,0.0005698972,0.0001644295,0.001786569,0.0002279222],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00009266986,0.00007779762,0.0005398619,0.04937923,0.0001740562,0.0001166471,0.0002862739,0.0004138372,0.0003335404,0.01412051,0.03354496,0.9009205],"study_design_scores_gemma":[0.00001772702,0.0001171816,0.001262711,0.02465578,0.0002568342,0.0005879574,0.0004180486,0.0001719663,0.0003118061,0.004335397,0.9678226,0.00004208005],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.0001072173,0.9978928,0.0003070315,0.0004849539,0.0001070418,0.00001020102,0.00002907824,0.000008015,0.001053627],"genre_scores_gemma":[0.0007362419,0.9981734,0.000569218,0.0002526114,0.00009050578,0.00001209925,0.00004331318,0.000004038174,0.0001185109],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.008820729,"threshold_uncertainty_score":0.02490926,"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."}}