{"id":"W1526785773","doi":"","title":"Building predictors from vertically distributed data","year":2004,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":30,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"","keywords":"Computer science; Data mining; Raw data; Voting; Majority rule; Variety (cybernetics); Decision tree; Range (aeronautics); Tree (set theory); Volume (thermodynamics); Distributed database; Data modeling; Artificial intelligence; Distributed computing; Database","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":[],"consensus_categories":[],"category_scores_codex":[0.00008252116,0.00006470047,0.00006464429,0.00001643737,0.00008115231,0.0001783719,0.00211293,0.0000257116,0.00001777194],"category_scores_gemma":[0.00005520292,0.00005480697,0.00001187687,0.0002258139,0.00002522393,0.0005975531,0.0009903802,0.00006089358,0.00008572578],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002209219,"about_ca_system_score_gemma":0.00005624987,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003281755,"about_ca_topic_score_gemma":0.0000128555,"domain_scores_codex":[0.9991729,0.000005911267,0.0001252312,0.00039547,0.0001479992,0.000152523],"domain_scores_gemma":[0.9983549,0.00004747991,0.00002028033,0.001462196,0.00002113841,0.0000940053],"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":[0.000001591247,0.0002254617,0.0005944569,0.000002319071,0.00005011797,0.0000141033,0.0001180402,0.0002611442,0.002311373,0.8447612,0.01399364,0.1376666],"study_design_scores_gemma":[0.001142649,0.00007019516,0.03192271,0.00004894118,0.00003243226,0.00001103531,0.00003019864,0.7457108,0.00605567,0.08829442,0.1261308,0.0005502246],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.009114846,0.00001581066,0.9875345,0.002094085,0.00009708681,0.00004723702,0.0005232544,0.0002697968,0.0003034313],"genre_scores_gemma":[0.164645,0.000003339694,0.834594,0.000189012,0.00006028009,0.000005172425,0.0004862635,0.000003665528,0.00001323806],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7564667,"threshold_uncertainty_score":0.3926386,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03002434051199953,"score_gpt":0.2775214862251876,"score_spread":0.2474971457131881,"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."}}