{"id":"W2159694214","doi":"10.1007/s10618-005-0013-7","title":"Discovering Classification from Data of Multiple Sources","year":2006,"lang":"en","type":"article","venue":"Data Mining and Knowledge Discovery","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":false,"ca_institutions":"Western University","funders":"Hong Kong University of Science and Technology","keywords":"Computer science; Class (philosophy); Artificial intelligence; Perspective (graphical); Machine learning; Supervised learning; Test data; Labeled data; Semi-supervised learning; Data mining; Artificial neural network","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":[0.0002407584,0.0001277773,0.0001717073,0.0000989292,0.0001088668,0.000360766,0.002715456,0.00006217286,0.000002267426],"category_scores_gemma":[0.0001747999,0.0001123532,0.00001586423,0.0002278161,0.0001380992,0.003468326,0.002970872,0.00006351536,0.000007896276],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000109065,"about_ca_system_score_gemma":0.00005834935,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004136408,"about_ca_topic_score_gemma":0.0003829455,"domain_scores_codex":[0.9986714,0.00003401692,0.0003004696,0.0007015095,0.0001340438,0.000158582],"domain_scores_gemma":[0.99664,0.0002935807,0.0001808924,0.00283604,0.00002525467,0.00002427116],"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":[0.00003563048,0.0006630691,0.2990901,0.0001281116,0.0001036389,0.000004766222,0.00233365,0.00001351238,0.02894267,0.0655508,0.04203899,0.5610951],"study_design_scores_gemma":[0.001411599,0.00007814277,0.3370076,0.0002936642,0.00008128853,0.00000501362,0.005904335,0.5673396,0.01371308,0.004187681,0.06907333,0.0009046807],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.744359,0.003202294,0.2486116,0.000307436,0.0002800949,0.0001064621,0.001488224,0.0002547168,0.001390118],"genre_scores_gemma":[0.9768553,0.00009434215,0.01969271,0.000006577824,0.00008133326,0.000004837763,0.002902986,0.000007581978,0.0003542787],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5673261,"threshold_uncertainty_score":0.5046038,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09401072320475932,"score_gpt":0.3028926707297767,"score_spread":0.2088819475250174,"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."}}