{"id":"W2057634750","doi":"10.9708/jksci.2012.17.2.139","title":"Probabilistic filtering for a biological knowledge discovery system with text mining and automatic inference","year":2012,"lang":"en","type":"article","venue":"Journal of the Korea Society of Computer and Information","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kootenay Association for Science & Technology","funders":"","keywords":"Computer science; Probabilistic logic; False positive paradox; Data mining; Inference; Event (particle physics); Knowledge extraction; Set (abstract data type); Information extraction; False positives and false negatives; Artificial intelligence; Information retrieval; Machine learning","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":[0.0002617885,0.000056472,0.0001153808,0.00001037883,0.00005114113,0.00002403391,0.00006958948,0.00006027925,1.42995e-7],"category_scores_gemma":[0.00003841608,0.00002859204,0.00005771607,0.00002718607,0.0001109096,0.00004728424,0.00006875629,0.00003551119,3.565139e-8],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000007129416,"about_ca_system_score_gemma":0.0000269644,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":5.629838e-7,"about_ca_topic_score_gemma":1.957105e-7,"domain_scores_codex":[0.9996126,0.00001828517,0.0002077631,0.00002944347,0.0000524841,0.00007942766],"domain_scores_gemma":[0.9995784,0.00005618912,0.0002184031,0.00005035288,0.0000665283,0.00003010206],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0005173776,0.0003022271,0.06426547,0.006853681,0.0009371867,2.332541e-7,0.03088168,0.0005035784,0.01564191,0.002477029,0.01261243,0.8650072],"study_design_scores_gemma":[0.008166598,0.009353069,0.5927179,0.004688902,0.0003728941,0.001573895,0.0145523,0.3156922,0.01399935,0.0002399607,0.03760894,0.001033889],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8525886,0.0002683714,0.146883,0.00006351549,0.00008962824,0.00007113013,0.000003372779,0.00000296453,0.00002939267],"genre_scores_gemma":[0.9714639,0.00004470552,0.02832805,0.00005129414,0.0001022373,0.000002189986,0.000002665514,0.000001528355,0.000003439359],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8639733,"threshold_uncertainty_score":0.116595,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01681352981951741,"score_gpt":0.2486235295802787,"score_spread":0.2318099997607612,"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."}}