{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.00136455,0.0005602809,0.0007870269,0.0003267716,0.0001981523,0.0006356783,0.04107986,0.0007914641,0.000002440193],"category_scores_gemma":[0.002919003,0.0004959702,0.00005053135,0.000236085,0.00009874722,0.0002626318,0.1732493,0.001227336,0.00001119899],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006845332,"about_ca_system_score_gemma":0.00003313758,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005299849,"about_ca_topic_score_gemma":0.001110183,"domain_scores_codex":[0.9959438,0.00007956061,0.0006789579,0.002277092,0.0004327261,0.0005878349],"domain_scores_gemma":[0.9762828,0.001598552,0.000404389,0.02159976,0.00003960592,0.00007483785],"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":[0.00001859864,0.00001132616,0.0001638064,0.000373937,0.000359156,0.000169716,0.00002342825,0.008547064,0.0000011309,0.00503249,0.07258614,0.9127132],"study_design_scores_gemma":[0.0002641205,0.00003071102,0.00001371593,0.0009056051,0.00004619596,0.000007713343,0.000001853637,0.7341551,3.45774e-7,0.0775458,0.1866205,0.0004083004],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.000001246342,0.01975347,0.967056,0.001935604,0.006110229,0.0009591749,0.001258477,0.0007564631,0.002169313],"genre_scores_gemma":[0.1231034,0.1139577,0.4953991,0.002251844,0.03860475,0.0008380775,0.1660175,0.002054601,0.05777306],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9123049,"threshold_uncertainty_score":0.9997492,"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."}}