{"id":"W4391175008","doi":"10.56367/oag-041-10846","title":"Reducing data volume in big data: Parallel processing based data filtering techniques","year":2024,"lang":"en","type":"article","venue":"Open Access Government","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University","funders":"","keywords":"Volume (thermodynamics); Big data; Computer science; Data processing; Data mining; Database","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","scholarly_communication","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.004934571,0.0002958401,0.0004361033,0.00009468958,0.0006897778,0.001295185,0.01722486,0.0002051557,0.0009054791],"category_scores_gemma":[0.001410454,0.0002747226,0.00001578962,0.0006372646,0.0000714398,0.007901988,0.0424671,0.001122294,0.0002267648],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001110604,"about_ca_system_score_gemma":0.002258806,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02580374,"about_ca_topic_score_gemma":0.01575965,"domain_scores_codex":[0.9944676,0.0004902509,0.001309108,0.00197524,0.0009437994,0.0008139558],"domain_scores_gemma":[0.9923086,0.0005219053,0.0003472055,0.006530871,0.00006391245,0.0002275631],"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":[0.0001477561,0.0001663398,0.04507476,0.002914621,0.00002807869,0.000159454,0.0009888175,0.0001115157,0.0004543749,0.0001257478,0.1923315,0.757497],"study_design_scores_gemma":[0.0001171125,0.00002907211,0.00139493,0.006237304,0.00003034135,0.000001818699,0.002379334,0.4804447,0.0004683202,0.0001898913,0.5083126,0.0003945041],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07262989,0.01771085,0.3952937,0.2002292,0.02843472,0.05246691,0.06637901,0.004377497,0.1624782],"genre_scores_gemma":[0.9482637,0.0006974958,0.03427287,0.003832829,0.002305581,0.0009574495,0.005660534,0.0002215723,0.003787955],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8756338,"threshold_uncertainty_score":0.9999705,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.6516426195564557,"score_gpt":0.5994076944851713,"score_spread":0.05223492507128447,"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."}}