{"id":"W4385078254","doi":"10.18280/isi.280303","title":"Os-ETL: A High-Efficiency, Open-Scala Solution for Integrating Heterogeneous Data in Large-Scale Data Warehousing","year":2023,"lang":"en","type":"article","venue":"Ingénierie des systèmes d information","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"University of Tlemcen","keywords":"Data warehouse; Scala; Computer science; Database; Scale (ratio); Operating system; Java; Geography","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005102562,0.001859001,0.0009080271,0.001513034,0.001795853,0.004368064,0.006553859,0.001116532,0.007068001],"category_scores_gemma":[0.007886446,0.001468642,0.002572869,0.002639273,0.002699503,0.007972743,0.008636454,0.00383539,0.005146979],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002567679,"about_ca_system_score_gemma":0.004565266,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0154546,"about_ca_topic_score_gemma":0.01166093,"domain_scores_codex":[0.9964012,0.0004306244,0.0003529922,0.0007970771,0.001590253,0.000427885],"domain_scores_gemma":[0.9947476,0.0009199585,0.0004570173,0.002222189,0.001027141,0.0006260331],"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":[0.002612579,0.001167656,0.0211808,0.001672141,0.001118772,0.002316994,0.004605216,0.1009846,0.09535877,0.1412975,0.2412446,0.3864402],"study_design_scores_gemma":[0.0005129352,0.0002593625,0.005388426,0.0001696319,0.0001455413,0.0004968197,0.0007544244,0.5492404,0.06856041,0.08311955,0.2909686,0.0003839625],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"software","genre_scores_codex":[0.01117456,0.0001632418,0.8708575,0.000866661,0.0002065931,0.0004572615,0.001512276,0.1080356,0.006726205],"genre_scores_gemma":[0.108195,0.0005334977,0.8375707,0.00101369,0.0002276952,0.0007078384,0.01407662,0.02357763,0.01409739],"genre_candidate":"software","genre_consensus":null,"teacher_disagreement_score":0.0154546,"threshold_uncertainty_score":0.03072929,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05695652818585403,"score_gpt":0.3091447065465073,"score_spread":0.2521881783606533,"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."}}