{"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":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.002219,0.0001883179,0.00024119,0.000320712,0.0006032753,0.001462014,0.004924208,0.0000948366,0.000003837178],"category_scores_gemma":[0.0004529119,0.000186205,0.00002580444,0.001420491,0.00006083551,0.0108587,0.004653102,0.0001437949,0.00008825605],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000164626,"about_ca_system_score_gemma":0.000184332,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005135745,"about_ca_topic_score_gemma":0.000419729,"domain_scores_codex":[0.9978398,0.00005551155,0.0007506673,0.0005327431,0.0002897232,0.0005315421],"domain_scores_gemma":[0.9969175,0.0001643683,0.0003154885,0.002379617,0.0001450752,0.00007798726],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001746624,0.0001405921,0.0003459585,0.0002529928,0.00002655689,0.000004846898,0.009334274,0.002239138,0.0002392916,0.009682846,0.01002386,0.9676922],"study_design_scores_gemma":[0.0004636261,0.00004531928,0.0007095261,0.0001546117,0.000006957509,0.00002008922,0.0005639314,0.9848645,0.0001332395,0.001377019,0.01143408,0.0002270789],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01354482,0.00003717213,0.9827715,0.0003094702,0.0003465101,0.0008097318,0.00147073,0.0003967258,0.0003133247],"genre_scores_gemma":[0.5695388,0.00002670945,0.4159777,0.0002281585,0.0001005514,0.0002680857,0.01380057,0.00002294196,0.00003645507],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9826254,"threshold_uncertainty_score":0.9995745,"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."}}