{"id":"W2610342131","doi":"10.12688/f1000research.11389.2","title":"PubRunner: A light-weight framework for updating text mining results","year":2017,"lang":"en","type":"preprint","venue":"F1000Research","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"Canada's Michael Smith Genome Sciences Centre; University of British Columbia","funders":"U.S. National Library of Medicine; National Institutes of Health","keywords":"Computer science; Upload; Workflow; Word2vec; Biomedical text mining; Data science; Field (mathematics); Domain (mathematical analysis); Information retrieval; World Wide Web; Text mining; Data mining; Artificial intelligence","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"not_applicable","genre":"software","about_ca_system":false,"about_ca_topic":false,"confidence":"low","status":"direct model label, unvalidated"},{"model":"gpt","categories":[],"domain":null,"study_design":"not_applicable","genre":"software","about_ca_system":false,"about_ca_topic":false,"confidence":"low","status":"direct model label, unvalidated"}],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.001877107,0.0004031728,0.0004887346,0.0001568958,0.000555208,0.000355426,0.001934393,0.001708275,0.00003659409],"category_scores_gemma":[0.01133959,0.0003542596,0.0003184699,0.00007564647,0.0004101149,0.00000348156,0.002996876,0.001077557,0.00003830336],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004706404,"about_ca_system_score_gemma":0.0006084605,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000618725,"about_ca_topic_score_gemma":0.00003801672,"domain_scores_codex":[0.9964535,0.0001848292,0.0005425634,0.001297487,0.0005604316,0.0009611421],"domain_scores_gemma":[0.9966101,0.000376727,0.0003626159,0.001994492,0.0003653609,0.0002907153],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.002105801,0.0002994368,0.00144044,0.00107683,0.0007644271,0.00007660664,0.001170957,0.00003497521,0.02989418,0.002138534,0.6451917,0.3158061],"study_design_scores_gemma":[0.001248519,0.0006866428,0.000973282,0.0008548964,0.00005023173,0.00001337865,0.000509332,0.0005346027,0.03372594,0.00986633,0.9507315,0.0008053843],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6012047,0.04191676,0.1200601,0.08418099,0.01335601,0.009018985,0.005391632,0.001172875,0.123698],"genre_scores_gemma":[0.7147489,0.001971665,0.2485941,0.0003980357,0.008397009,0.001223322,0.003059573,0.0002924885,0.02131486],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3150007,"threshold_uncertainty_score":0.9998909,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07276717202123249,"score_gpt":0.3943506542953737,"score_spread":0.3215834822741412,"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."}}