{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005624347,0.001409289,0.002243691,0.01830985,0.001482627,0.006336865,0.002386163,0.002665503,0.001637237],"category_scores_gemma":[0.02580046,0.0008612662,0.002122977,0.01720483,0.001049047,0.008512229,0.002439776,0.002515985,0.002108492],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001028792,"about_ca_system_score_gemma":0.001895905,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002427358,"about_ca_topic_score_gemma":0.003026251,"domain_scores_codex":[0.9932795,0.001063304,0.0007128327,0.001352261,0.003217558,0.0003745958],"domain_scores_gemma":[0.9758523,0.01339128,0.002098589,0.003943132,0.00429087,0.0004238674],"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":[0.001166684,0.001317031,0.1555344,0.001944462,0.00129095,0.002652186,0.001920364,0.007674853,0.02687825,0.006253668,0.0127994,0.7805677],"study_design_scores_gemma":[0.000452867,0.00126247,0.1515622,0.002250052,0.007240615,0.0065847,0.01008784,0.4500056,0.1169482,0.1714756,0.08161869,0.0005113019],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3314754,0.006971492,0.6293526,0.004597206,0.000682692,0.0009879175,0.01468221,0.004189003,0.007061521],"genre_scores_gemma":[0.492104,0.003294614,0.4794604,0.0004703014,0.0007005545,0.0008244904,0.02004827,0.0003483991,0.002748897],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01830985,"threshold_uncertainty_score":0.0297448,"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."}}