{"id":"W2947100013","doi":"10.1186/s12859-019-2801-x","title":"Automated assessment of biological database assertions using the scientific literature","year":2019,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Bhabha Atomic Research Centre; Australian Research Council","keywords":"Computer science; Consistency (knowledge bases); Information retrieval; Assertion; Relevance (law); Relation (database); Biological database; Classifier (UML); Set (abstract data type); Data mining; Data science; Database; Bioinformatics; Artificial intelligence; Biology; 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004426983,0.0001072352,0.000129243,0.00004817322,0.0001155558,0.00006947965,0.0002848749,0.0001693743,0.00001849278],"category_scores_gemma":[0.0001454799,0.00006089222,0.00007749702,0.0002525433,0.0002685307,0.00000752863,0.0001865434,0.0001090211,0.000009212535],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000009222084,"about_ca_system_score_gemma":0.0001609866,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002232228,"about_ca_topic_score_gemma":0.000003435245,"domain_scores_codex":[0.999163,0.00005313237,0.0002928023,0.0001377198,0.000169841,0.0001835211],"domain_scores_gemma":[0.9991724,0.00003972583,0.0001443886,0.0004960472,0.0001032006,0.00004418737],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00009783902,0.0004672158,0.128103,0.0009288773,0.0002332664,0.000002830237,0.001066678,0.002726504,0.8412489,0.002511468,0.01692749,0.005685956],"study_design_scores_gemma":[0.0006862209,0.000361398,0.02145644,0.0001793719,0.00003331425,0.0000448169,0.001313499,0.9382694,0.01406829,0.00004206915,0.02325049,0.0002947079],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9585317,0.0003611254,0.03956912,0.00005168478,0.0004221301,0.0002407236,0.0001274993,0.00006182243,0.000634165],"genre_scores_gemma":[0.7415978,0.00003415979,0.2573789,0.0001172768,0.0000470255,0.000005998515,0.0006057681,0.000007103456,0.0002060295],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9355429,"threshold_uncertainty_score":0.2483113,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0457625408629511,"score_gpt":0.3421514158978473,"score_spread":0.2963888750348961,"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."}}