{"id":"W1983388548","doi":"10.1007/s10844-012-0229-0","title":"Reducing the size of databases for multirelational classification: a subgraph-based approach","year":2012,"lang":"en","type":"article","venue":"Journal of Intelligent Information Systems","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Ottawa; National Research Council Canada","funders":"","keywords":"Computer science; Database; Preprocessor; Tuple; Data mining; Relational database; Data pre-processing; Schema (genetic algorithms); Machine learning; Artificial intelligence","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":[0.01315602,0.00009464013,0.0002560618,0.0003467634,0.000139484,0.0001988294,0.0006326823,0.00003812372,0.00004219593],"category_scores_gemma":[0.004656446,0.00005300763,0.0002009454,0.0004730831,0.00007488031,0.002802125,0.00004558339,0.0001077341,0.00003717053],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005522048,"about_ca_system_score_gemma":0.0001003944,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001761263,"about_ca_topic_score_gemma":5.469178e-7,"domain_scores_codex":[0.9956981,0.0002415185,0.00234426,0.00006725924,0.001497825,0.0001510292],"domain_scores_gemma":[0.992221,0.003066357,0.002870416,0.0004178027,0.001339575,0.00008487319],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000794917,0.0008729892,0.01060915,0.0007332234,0.0004101403,2.288844e-7,0.01440112,0.1266103,0.0002621659,0.5515664,0.1996815,0.09405785],"study_design_scores_gemma":[0.0005697642,0.00009542419,0.0051646,0.0001332137,0.00005961199,0.00002908341,0.03524717,0.09476523,0.0007898001,0.0001884631,0.862817,0.000140605],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004732744,0.0003064755,0.98887,0.0005244779,0.001313708,0.0005585077,0.0001499434,0.000006727926,0.003537419],"genre_scores_gemma":[0.9915719,0.00001745093,0.007707572,0.0001888686,0.0002301157,0.00002564082,0.00005932944,0.000003561495,0.000195585],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9868391,"threshold_uncertainty_score":0.5574536,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3453831662634866,"score_gpt":0.421210654523675,"score_spread":0.07582748826018837,"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."}}