{"id":"W2397149926","doi":"10.1007/978-1-4939-0709-0_5","title":"Biological Information Extraction and Co-occurrence Analysis","year":2014,"lang":"en","type":"review","venue":"Methods in molecular biology","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":43,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Inference; Data science; Field (mathematics); Representation (politics); String (physics); Information extraction; Information retrieval; Data mining; Artificial intelligence; Mathematics","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":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.001853561,0.0003872353,0.001412313,0.0005089637,0.00004737677,0.00002775406,0.0003259919,0.001508032,0.00001545293],"category_scores_gemma":[0.001532603,0.0002929156,0.0004070767,0.0005272646,0.0003962537,0.000003106523,0.0001933964,0.0004224398,0.00000970034],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002321758,"about_ca_system_score_gemma":0.00007698127,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001108985,"about_ca_topic_score_gemma":0.000003722102,"domain_scores_codex":[0.9960034,0.002236194,0.0007307898,0.0006063476,0.00006939197,0.0003538259],"domain_scores_gemma":[0.9987504,0.000267102,0.0003892898,0.0004583827,0.00004061923,0.00009422825],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000008285706,0.00001698687,0.0001138603,0.0004250142,0.0002852677,0.000002589634,0.000007357528,0.000001186423,0.0007241086,0.0001271021,0.00006984576,0.9982184],"study_design_scores_gemma":[0.0001380031,0.0002321216,0.00003082155,0.0001270113,0.0004056175,0.00003499606,0.000008574177,0.00002437878,0.0002470045,0.0001696146,0.9982419,0.0003399752],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.00002208142,0.5198104,0.4796822,0.000008659439,0.0001145642,0.0001525645,0.00006652239,0.00001460559,0.0001284101],"genre_scores_gemma":[0.00001012719,0.7743151,0.2229175,0.0001208778,0.000048814,0.00008718365,0.002481752,0.000008389316,0.00001027576],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.998172,"threshold_uncertainty_score":0.9999523,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06840891714613861,"score_gpt":0.5014912274252321,"score_spread":0.4330823102790935,"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."}}