{"id":"W1999302328","doi":"10.1186/2041-1480-5-11","title":"Benchmarking infrastructure for mutation text mining","year":2014,"lang":"en","type":"article","venue":"Journal of Biomedical Semantics","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of New Brunswick","funders":"New Brunswick Innovation Foundation","keywords":"Computer science; Benchmarking; SPARQL; Information retrieval; Ontology; RDF; Data mining; Annotation; Benchmark (surveying); Data science; Semantic Web; Artificial intelligence","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0006177857,0.000109309,0.0002152809,0.00008417313,0.00006852764,0.00002108873,0.0002042632,0.000260769,0.00001402175],"category_scores_gemma":[0.001251881,0.00008074014,0.0001333506,0.0000965814,0.0002390578,0.000003195394,0.00004842495,0.0001277941,8.786549e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001113065,"about_ca_system_score_gemma":0.00007333892,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":6.072587e-7,"about_ca_topic_score_gemma":0.00000109122,"domain_scores_codex":[0.9989323,0.00004670888,0.0004121781,0.0001358959,0.0002637201,0.0002091844],"domain_scores_gemma":[0.9991508,0.000118849,0.0003119065,0.0001119654,0.0001543898,0.0001521023],"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":[0.0002246206,0.0001196678,0.00167283,0.0001386139,0.000188362,0.0000183974,0.0003253997,0.00005702563,0.1187147,0.000163243,0.06100924,0.8173679],"study_design_scores_gemma":[0.002551642,0.004149457,0.005962502,0.0001892815,0.0001214891,0.0005095882,0.0006196965,0.005522761,0.01301655,0.001472754,0.9655734,0.0003108269],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6374412,0.0002937525,0.359787,0.001413506,0.0009126933,0.00005754245,0.00000548822,0.000006973023,0.00008183174],"genre_scores_gemma":[0.9158005,0.00006183757,0.08158302,0.0004169014,0.002036773,0.000001452145,0.00003242837,0.00001308129,0.00005406978],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9045642,"threshold_uncertainty_score":0.3292488,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.008037719161641739,"score_gpt":0.2664438411905976,"score_spread":0.2584061220289558,"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."}}