{"id":"W4385573833","doi":"10.18653/v1/2022.louhi-1.25","title":"Integration of Heterogeneous Knowledge Sources for Biomedical Text Processing","year":2022,"lang":"en","type":"article","venue":"","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"","keywords":"Leverage (statistics); Interoperability; Computer science; Knowledge graph; Graph; Task (project management); Knowledge integration; Artificial intelligence; Domain knowledge; Data science; Theoretical computer science; World Wide Web; Engineering; Systems engineering","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":[0.00267039,0.001258428,0.0009736417,0.004569767,0.0007396952,0.001954476,0.001231409,0.001091184,0.00271165],"category_scores_gemma":[0.01069848,0.0005580239,0.001448716,0.00396681,0.0006784691,0.005925648,0.005436676,0.001798105,0.001652133],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005933195,"about_ca_system_score_gemma":0.001116908,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00210258,"about_ca_topic_score_gemma":0.004806542,"domain_scores_codex":[0.9982765,0.0005945387,0.0001951353,0.0004175665,0.00044044,0.00007587564],"domain_scores_gemma":[0.9960317,0.002015094,0.0001964883,0.0009830993,0.0006715328,0.0001020046],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0004271117,0.0004781235,0.005054286,0.0007787381,0.0006228673,0.0009452952,0.000729157,0.05770606,0.02359547,0.0163652,0.01038334,0.8829144],"study_design_scores_gemma":[0.00008421391,0.0001933954,0.003942497,0.0002739288,0.0005487296,0.0006758957,0.0007115242,0.7645589,0.04238799,0.1426894,0.04381843,0.0001151554],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02363465,0.001215055,0.9645353,0.0007956383,0.0001158016,0.0002137591,0.001057,0.005149754,0.003283035],"genre_scores_gemma":[0.3533747,0.001565752,0.6324855,0.0005905871,0.000143155,0.00032844,0.006602126,0.0008548371,0.004054807],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004569767,"threshold_uncertainty_score":0.01412255,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02437599792128227,"score_gpt":0.3039290350910197,"score_spread":0.2795530371697375,"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."}}