{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003472974,0.001270723,0.002381723,0.001384118,0.0007644847,0.001678044,0.002530586,0.0008415711,0.001628842],"category_scores_gemma":[0.006106324,0.0006667906,0.0015241,0.003788197,0.0007001387,0.003191518,0.001457145,0.001324726,0.0008334173],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008460581,"about_ca_system_score_gemma":0.001906502,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003987713,"about_ca_topic_score_gemma":0.002977726,"domain_scores_codex":[0.9978589,0.0005195967,0.0001529009,0.0003734902,0.0008902134,0.0002048426],"domain_scores_gemma":[0.9980356,0.0009899439,0.000111547,0.0002918118,0.0004852868,0.00008579989],"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":[0.0002559033,0.0002180935,0.003957227,0.001561598,0.0002660696,0.0001767573,0.0001460182,0.2962229,0.002374611,0.03698489,0.03413065,0.6237053],"study_design_scores_gemma":[0.00009038483,0.00009558384,0.001362098,0.0001765624,0.00008128249,0.00025205,0.0001113939,0.8870498,0.002871338,0.06303135,0.04482242,0.0000557819],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"review","genre_scores_codex":[0.01343997,0.06508277,0.9036577,0.001790977,0.0004677831,0.0001594022,0.0003518453,0.004832126,0.01021736],"genre_scores_gemma":[0.3283982,0.06667931,0.5921652,0.0009739298,0.001529611,0.0006617766,0.002199139,0.00270928,0.004683571],"genre_candidate":"review","genre_consensus":null,"teacher_disagreement_score":0.003987713,"threshold_uncertainty_score":0.01836705,"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."}}