{"id":"W2520572539","doi":"10.1101/073460","title":"Semi-Automated Identification of Ontological Labels in the Biomedical Literature with goldi","year":2016,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Public Health Ontario; University of Toronto; University of Ottawa; Centre for Addiction and Mental Health","funders":"","keywords":"Computer science; Leverage (statistics); Identification (biology); Parsing; Scope (computer science); Ontology; Data science; Function (biology); Dependency grammar; Artificial intelligence; Information retrieval; Natural language processing; Epistemology; Programming language","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":[0.008120967,0.001295127,0.001331524,0.02047518,0.001963797,0.004955871,0.001805346,0.001477993,0.005298978],"category_scores_gemma":[0.03270617,0.0007555118,0.001776736,0.008566969,0.001266685,0.003217908,0.006068852,0.001877715,0.005454169],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002009026,"about_ca_system_score_gemma":0.004303107,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00469479,"about_ca_topic_score_gemma":0.01001591,"domain_scores_codex":[0.9936292,0.001729193,0.000849183,0.001508214,0.001968393,0.0003158834],"domain_scores_gemma":[0.9822916,0.01028564,0.001784049,0.002215965,0.002996865,0.0004259405],"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":[0.0004933781,0.0002655012,0.01646544,0.003088345,0.0003457929,0.0006124502,0.002942255,0.007857165,0.02826187,0.04547291,0.1155903,0.7786047],"study_design_scores_gemma":[0.0001823246,0.0002221188,0.01766917,0.001345888,0.0003571666,0.001485379,0.003317263,0.4983209,0.06313699,0.1772669,0.2363807,0.0003152333],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.04127147,0.002382473,0.862084,0.003158011,0.0003220627,0.0009830145,0.02035729,0.05861675,0.01082495],"genre_scores_gemma":[0.04500936,0.0002976309,0.9372693,0.000238756,0.00007866266,0.0003419757,0.01422972,0.0008399735,0.001694598],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.02047518,"threshold_uncertainty_score":0.04294831,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01025260645618114,"score_gpt":0.2417548716346633,"score_spread":0.2315022651784822,"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."}}