{"id":"W2111255192","doi":"","title":"Applying Probabilistic Thematic Clustering for Classification in the TREC 2005 Genomics Track","year":2005,"lang":"en","type":"article","venue":"","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"","keywords":"Computer science; Artificial intelligence; Feature selection; Classifier (UML); Cluster analysis; Categorization; Naive Bayes classifier; Test set; Machine learning; Pattern recognition (psychology); Data mining; Natural language processing; Support vector machine","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":[0.009641312,0.0008768754,0.0009750935,0.00474907,0.001980407,0.001803949,0.001739069,0.001708659,0.001315699],"category_scores_gemma":[0.01631489,0.0003701572,0.001404206,0.003975792,0.0006454828,0.002649975,0.0009505239,0.001275846,0.001032252],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002594422,"about_ca_system_score_gemma":0.002099422,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02775389,"about_ca_topic_score_gemma":0.02531126,"domain_scores_codex":[0.9916414,0.004200011,0.0004941955,0.001103144,0.002029985,0.0005312413],"domain_scores_gemma":[0.9901183,0.005988348,0.0003948864,0.0007941818,0.0024638,0.0002404447],"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":[0.001263131,0.0009243899,0.0271684,0.0005539322,0.0003436895,0.0004107072,0.001410747,0.08924966,0.0226535,0.008493057,0.04778267,0.7997462],"study_design_scores_gemma":[0.0001226092,0.000348706,0.01781772,0.0000661966,0.0001395163,0.0003530261,0.001238149,0.9255542,0.02421121,0.01496965,0.01506745,0.0001116057],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3645039,0.001973622,0.6024582,0.002369863,0.0004614607,0.001494879,0.00567493,0.01048878,0.01057435],"genre_scores_gemma":[0.5215672,0.0004180102,0.465283,0.0002941605,0.0001476018,0.0005349255,0.008475767,0.0002956752,0.002983694],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.02775389,"threshold_uncertainty_score":0.05518466,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05130768496816875,"score_gpt":0.302721482534822,"score_spread":0.2514137975666533,"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."}}