{"id":"W4327884632","doi":"10.1007/978-3-031-29056-5_35","title":"Big Data Management for Machine Learning from Big Data","year":2023,"lang":"en","type":"book-chapter","venue":"Lecture notes in networks and systems","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Manitoba","funders":"","keywords":"Big data; Computer science; Metadata; Schema (genetic algorithms); Data warehouse; Data science; Unstructured data; Artificial intelligence; Schema evolution; Machine learning; Data collection; Data modeling; Database schema; Data mining; Database; Database design; World Wide Web","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":[0.001949223,0.0007361721,0.0009557373,0.001017764,0.0007602579,0.003254998,0.002232112,0.001087696,0.009237528],"category_scores_gemma":[0.004037993,0.0007549223,0.0007330701,0.002389185,0.001069274,0.007466065,0.003127569,0.003578408,0.005344136],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009407179,"about_ca_system_score_gemma":0.0009225335,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004990748,"about_ca_topic_score_gemma":0.0006738761,"domain_scores_codex":[0.9988496,0.0002156774,0.00009946043,0.0001796777,0.0005769075,0.00007870436],"domain_scores_gemma":[0.9976948,0.0007588634,0.0001053572,0.001117406,0.0002098157,0.0001137722],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001761813,0.0001253165,0.0006823862,0.0006155552,0.0001019424,0.0002211359,0.0003026159,0.01132521,0.004938642,0.2568107,0.2126225,0.5120778],"study_design_scores_gemma":[0.00002522359,0.00005386972,0.0006488631,0.0001977817,0.00003518371,0.0004868463,0.0001001471,0.1243768,0.008654058,0.5535841,0.3117963,0.00004087583],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002772829,0.01038965,0.9548497,0.00482961,0.001288016,0.0001512435,0.00123679,0.006454479,0.01802778],"genre_scores_gemma":[0.1290634,0.02053393,0.7490654,0.004141705,0.003626045,0.0006691099,0.008879541,0.003371958,0.08064897],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.009237528,"threshold_uncertainty_score":0.03090262,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1311760100967066,"score_gpt":0.2767713492805602,"score_spread":0.1455953391838536,"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."}}