{"id":"W1623534659","doi":"10.1186/s40537-015-0021-4","title":"Meta-MapReduce for scalable data mining","year":2015,"lang":"en","type":"article","venue":"Journal Of Big Data","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa; Dalhousie University","funders":"","keywords":"Computer science; Scalability; Big data; AdaBoost; Machine learning; Node (physics); Programming paradigm; Cloud computing; Artificial intelligence; Data mining; Database; Programming language; Operating system; Support vector machine","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":["open_science"],"consensus_categories":[],"category_scores_codex":[0.003717553,0.00008321714,0.0002316502,0.0001014981,0.00006249354,0.000255979,0.006078374,0.00003282447,0.000004188959],"category_scores_gemma":[0.00157337,0.00006043595,0.0000360789,0.0001960792,0.00001554142,0.002288494,0.001611671,0.0001410809,0.00001374574],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001610972,"about_ca_system_score_gemma":0.000311215,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001912882,"about_ca_topic_score_gemma":0.000008452446,"domain_scores_codex":[0.9987145,0.00009397454,0.0003736098,0.0003087303,0.0003594234,0.0001497298],"domain_scores_gemma":[0.9959646,0.000196579,0.0004605764,0.003005233,0.0002126818,0.0001603361],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00002961203,0.00009486675,0.0003078636,0.00001900053,0.0003989414,0.0000104142,0.0001738729,0.0001030523,0.0001926153,0.0007281177,0.6457739,0.3521678],"study_design_scores_gemma":[0.0004929327,0.0001081492,0.0002124729,0.00001675188,0.0003094492,0.0001248153,0.00005063772,0.2155005,0.00007421103,0.0004606536,0.7825497,0.00009965597],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0006409503,0.001396228,0.9891389,0.006779524,0.001139074,0.00006552815,0.0003387498,0.00002414708,0.000476882],"genre_scores_gemma":[0.09742723,0.00006890715,0.8990729,0.000378071,0.001384835,0.000002344654,0.001099309,0.00001506415,0.0005513693],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3520681,"threshold_uncertainty_score":0.9992992,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.6436468009513665,"score_gpt":0.3948568341215879,"score_spread":0.2487899668297786,"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."}}