{"id":"W3203751410","doi":"10.1093/database/baab062","title":"Classifying domain-specific text documents containing ambiguous keywords","year":2021,"lang":"en","type":"article","venue":"Database","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"Eunice Kennedy Shriver National Institute of Child Health and Human Development","keywords":"Computer science; Set (abstract data type); Domain (mathematical analysis); Information retrieval; Artificial intelligence; Naive Bayes classifier; Overfitting; Identifier; Machine learning; Support vector machine; Ambiguity; 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":[0.00021287,0.0001571609,0.0001655211,0.00003015041,0.0001342821,0.00005419549,0.0002031397,0.0001393788,0.0001771662],"category_scores_gemma":[0.0001085496,0.0001482052,0.00007361401,0.0001246979,0.0001392653,0.000004884457,0.0003193983,0.000153343,0.00007622842],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001728815,"about_ca_system_score_gemma":0.00009049035,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003018893,"about_ca_topic_score_gemma":0.00003458015,"domain_scores_codex":[0.9987103,0.00008525354,0.0002093727,0.0004745297,0.0001791576,0.000341434],"domain_scores_gemma":[0.9991483,0.00002031332,0.00006026316,0.0005746381,0.00006178077,0.0001346743],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001854048,0.0001871467,0.003533557,0.00004463811,0.0001255629,0.0005697726,0.000142285,0.00000223147,0.7762683,0.001037699,0.07155318,0.1463502],"study_design_scores_gemma":[0.0008068217,0.0001105699,0.001420866,0.00004226454,0.000009397978,0.00007289772,0.0007003581,0.000004922985,0.05204681,0.00006977453,0.9444986,0.0002167228],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.95916,0.008451284,0.02361323,0.0007899738,0.0008023744,0.0001138328,0.0003257576,0.0000791936,0.006664358],"genre_scores_gemma":[0.9551764,0.001320261,0.03509782,0.001620728,0.0006496265,0.00003193194,0.003889326,0.00004177681,0.002172184],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8729454,"threshold_uncertainty_score":0.6043631,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02704470169982052,"score_gpt":0.290375614861075,"score_spread":0.2633309131612545,"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."}}