{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0007329639,0.000291021,0.0003494157,0.0001414549,0.0006047818,0.001231969,0.0008594417,0.00008544207,0.000002659286],"category_scores_gemma":[0.00007170175,0.0002632217,0.00002786015,0.0002924228,0.0001260411,0.0006264779,0.001420894,0.0002281208,0.0000241272],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001193093,"about_ca_system_score_gemma":0.00001176957,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001496416,"about_ca_topic_score_gemma":0.000002355805,"domain_scores_codex":[0.9979899,0.0000638146,0.0007085014,0.0004747619,0.0002766469,0.0004863986],"domain_scores_gemma":[0.9984893,0.0003209823,0.000241859,0.0006694662,0.00007260102,0.0002058362],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000007079587,0.0001443264,0.0006572329,0.00025543,0.00004805838,0.00002243267,0.0207247,0.004406301,0.000006247502,0.1040274,0.006171396,0.8635294],"study_design_scores_gemma":[0.00007889443,0.000205511,0.0001681558,0.000314878,0.00000591823,0.00006280676,0.0004848461,0.9909047,0.00005012253,0.001404247,0.005991194,0.0003287291],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1510606,0.001282181,0.8449642,0.0006087986,0.00079866,0.0002343045,0.00001672236,0.0002631002,0.0007714407],"genre_scores_gemma":[0.954788,0.0001910794,0.04424425,0.0005382877,0.0001854096,0.000001084864,0.00001775313,0.000009615304,0.00002451684],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9864984,"threshold_uncertainty_score":0.999982,"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."}}