{"id":"W4402898151","doi":"10.1016/j.is.2024.102460","title":"Data Lakehouse: A survey and experimental study","year":2024,"lang":"en","type":"article","venue":"Information Systems","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":25,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Foundation for Innovation","keywords":"Computer science; Survey research; Data science; Psychology","routes":{"ca_aff":true,"ca_fund":true,"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":["scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.01029928,0.00007268968,0.0001335367,0.0002126558,0.00008388504,0.003033988,0.0007045482,0.00002174519,0.00004758056],"category_scores_gemma":[0.0005033645,0.00005103362,0.00001045356,0.0003929696,0.00002446288,0.0050951,0.0006615904,0.00004849445,0.001781812],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001766996,"about_ca_system_score_gemma":0.00002587341,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006114352,"about_ca_topic_score_gemma":0.000206184,"domain_scores_codex":[0.9977377,0.0003096543,0.0006779349,0.0002066723,0.0009724983,0.00009554423],"domain_scores_gemma":[0.9984728,0.00043092,0.00009256496,0.0008833306,0.00006949369,0.00005085908],"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":[0.00004683253,0.0002251671,0.01069032,0.0001280961,0.0001331323,0.00001535283,0.02760623,0.0001988152,0.000006657941,0.0163992,0.9057835,0.03876673],"study_design_scores_gemma":[0.000206731,0.00007111867,0.008069685,0.00001566077,0.000003842513,0.000007753752,0.03720115,0.01898548,0.000002871128,0.00002866941,0.935314,0.00009305626],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8863623,0.003334749,0.04689957,0.0005554418,0.009997536,0.003793343,0.008423107,0.0007818808,0.03985211],"genre_scores_gemma":[0.9988675,0.000003024787,0.00001552684,0.00007908206,0.00003815429,0.00002090525,0.0002912172,0.000002830298,0.0006818258],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1125052,"threshold_uncertainty_score":0.9989954,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4319128260972868,"score_gpt":0.4771378457812553,"score_spread":0.04522501968396853,"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."}}