{"id":"W2006341631","doi":"10.4018/jdm.2008100105","title":"Ontology for Data Mining and its Application to Mining Incomplete Data","year":2008,"lang":"en","type":"article","venue":"Journal of Database Management","topic":"Semantic Web and Ontologies","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"Saint Mary's University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Ontology; Computer science; Data mining; Knowledge extraction; Ontology-based data integration; Process ontology; Upper ontology; Domain (mathematical analysis); Data science; Domain knowledge; Information retrieval; Knowledge management","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0009938743,0.0001010521,0.0002142999,0.0001898066,0.0001316909,0.00005015377,0.002983863,0.00001909815,0.000001731869],"category_scores_gemma":[0.0001707797,0.0000878088,0.00001576454,0.0001615618,0.0000208614,0.001076544,0.0039272,0.00004811091,0.000003650156],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001713445,"about_ca_system_score_gemma":0.00002958795,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001028224,"about_ca_topic_score_gemma":0.00004245346,"domain_scores_codex":[0.9987327,0.00003618446,0.0003838473,0.0004108991,0.0002349837,0.0002014281],"domain_scores_gemma":[0.997817,0.000175171,0.0002588906,0.001586542,0.00007075823,0.0000916078],"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":[0.0001950039,0.0001919083,0.004135562,0.0004449156,0.0005060363,0.0008219731,0.001619506,0.00009032574,0.001432258,0.02325772,0.3103362,0.6569685],"study_design_scores_gemma":[0.002354247,0.0004321172,0.01305262,0.0002353427,0.0001911093,0.001031776,0.0009533845,0.4886021,0.0002581858,0.0002539621,0.4921493,0.0004859268],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03049919,0.0005654255,0.9646846,0.003348114,0.0002782781,0.0003034243,0.00008983574,0.00002176876,0.0002093484],"genre_scores_gemma":[0.1089294,0.0002675443,0.8896269,0.0008235847,0.0001442639,0.000008633914,0.0001378025,0.000006976069,0.0000549203],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6564826,"threshold_uncertainty_score":0.554481,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1642859759300605,"score_gpt":0.3422706804343884,"score_spread":0.1779847045043279,"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."}}