{"id":"W4400875444","doi":"10.3390/computers13070183","title":"Data Lakes: A Survey of Concepts and Architectures","year":2024,"lang":"en","type":"article","venue":"Computers","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":25,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University","funders":"Ministry of Higher Education and Scientific Research","keywords":"Data science; Survey data collection; Computer science; Geography; Mathematics; Statistics","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":[0.003203192,0.00005397546,0.0001318834,0.0001095186,0.00002426925,0.0002453555,0.001000204,0.00001441886,0.00004055122],"category_scores_gemma":[0.0006825961,0.00003759701,0.00001530636,0.0003063233,0.0001438973,0.0001218401,0.001005591,0.00004759247,0.00004009486],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000002567207,"about_ca_system_score_gemma":0.00002333706,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001644269,"about_ca_topic_score_gemma":0.0004464688,"domain_scores_codex":[0.9987191,0.0002286903,0.0002383808,0.000360957,0.0003707881,0.00008206982],"domain_scores_gemma":[0.9970598,0.002056944,0.0000373868,0.0007723561,0.00003263341,0.0000408551],"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":[0.00001083436,0.00001741055,0.001128938,0.00004532288,0.00004406226,0.00001402892,0.001150115,0.0001389422,0.00001466242,0.005754022,0.3700665,0.6216151],"study_design_scores_gemma":[0.0002382281,0.00008059528,0.145557,0.0001148545,0.00001609954,0.000007536014,0.0004075809,0.108063,0.00002809454,0.01396545,0.7313313,0.0001902458],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4132884,0.00356684,0.5700434,0.002919171,0.002881039,0.0003367874,0.003791872,0.0001417121,0.003030758],"genre_scores_gemma":[0.9970884,0.00001545923,0.002153528,0.0003471333,0.00002977218,6.073063e-7,0.0001134678,0.000003317232,0.0002482579],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6214249,"threshold_uncertainty_score":0.2365969,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3904131326033246,"score_gpt":0.4888631919173062,"score_spread":0.09845005931398154,"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."}}