{"id":"W22316296","doi":"10.1089/jmf.2011.1827","title":"Mining Large Data Sets on Grids: Issues and Prospects","year":2002,"lang":"en","type":"article","venue":"Computing and Informatics / Computers and Artificial Intelligence","topic":"Distributed and Parallel Computing Systems","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"","keywords":"Computer science; Computation; Grid; Knowledge extraction; Distributed computing; Data science; Grid computing; Data grid; Data mining; Scale (ratio)","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":[0.01275002,0.001319699,0.003755508,0.003387922,0.001295767,0.006229393,0.006245818,0.002466052,0.005069372],"category_scores_gemma":[0.0418864,0.001366749,0.002543093,0.01120844,0.001947265,0.01352701,0.00377631,0.002749862,0.002592533],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00139178,"about_ca_system_score_gemma":0.002373466,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006633153,"about_ca_topic_score_gemma":0.007704956,"domain_scores_codex":[0.9937888,0.002424545,0.000614543,0.001651291,0.001248061,0.0002728124],"domain_scores_gemma":[0.9399803,0.03678157,0.002016353,0.0131262,0.005847345,0.002248313],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.001163026,0.0007648727,0.06296282,0.002303494,0.001426328,0.001511911,0.001154682,0.1824235,0.00243397,0.06979336,0.08813602,0.585926],"study_design_scores_gemma":[0.0001491656,0.000191043,0.009049908,0.0003961355,0.00008439892,0.0008540206,0.002500114,0.6068925,0.001341949,0.323557,0.05489558,0.00008818619],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"other","genre_scores_codex":[0.1510474,0.03322861,0.6929386,0.08470788,0.002446783,0.0008421086,0.01730009,0.00790647,0.009582037],"genre_scores_gemma":[0.381497,0.01380256,0.5730766,0.003293256,0.002089852,0.0007177355,0.0205793,0.0006699253,0.004273732],"genre_candidate":"other","genre_consensus":null,"teacher_disagreement_score":0.01275002,"threshold_uncertainty_score":0.0674293,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07509896457680171,"score_gpt":0.3029576007569295,"score_spread":0.2278586361801278,"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."}}