{"id":"W4412689102","doi":"10.47297/taposatwsp2633-456911.20250605","title":"Optimizing Random Forest with Apache Spark: A Survey on Distributed Machine Learning and Big Data Scalability","year":2025,"lang":"en","type":"article","venue":"Theory and Practice of Science and Technology","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"","keywords":"SPARK (programming language); Scalability; Big data; Random forest; Computer science; Database; Operating system; Data science; Distributed computing; Machine learning; Programming language","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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01140724,0.00009956027,0.0001731222,0.000275116,0.000470306,0.0001345298,0.0006462879,0.00006513117,7.281176e-7],"category_scores_gemma":[0.01281652,0.00007210388,0.00000380516,0.001353588,0.002050256,0.0007711396,0.0007854177,0.0003371747,3.482834e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000009254008,"about_ca_system_score_gemma":0.0001130807,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001370073,"about_ca_topic_score_gemma":0.00005668826,"domain_scores_codex":[0.9984354,0.000512807,0.0001505924,0.0005616254,0.0001650656,0.0001745281],"domain_scores_gemma":[0.995922,0.0030731,0.0001434524,0.0006438614,0.000172372,0.00004521571],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00140159,0.0001375877,0.07874222,0.00005554616,0.00003225984,0.000004915797,0.0003126894,0.00006869704,0.00181597,0.4736936,0.00001826581,0.4437167],"study_design_scores_gemma":[0.01037972,0.003767141,0.3663277,0.0006425438,0.000335876,0.0006136883,0.005877755,0.4788099,0.006582225,0.08951258,0.03572509,0.001425746],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4004462,0.001078171,0.5850613,0.01097013,0.0000867141,0.0002676881,0.00005645493,0.0001769897,0.00185633],"genre_scores_gemma":[0.9917822,0.0003020955,0.007780851,0.00007242877,0.000003901116,0.000002755541,0.0000276362,0.000002163779,0.00002590306],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5913361,"threshold_uncertainty_score":0.995499,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03292571789572647,"score_gpt":0.3094492215514746,"score_spread":0.2765235036557482,"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."}}