{"id":"W2958192375","doi":"10.48550/arxiv.1307.8057","title":"Extracting Connected Concepts from Biomedical Texts using Fog Index","year":2013,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University","funders":"","keywords":"Readability; Categorization; Filter (signal processing); Computer science; Index (typography); Rank (graph theory); Artificial intelligence; Natural language processing; Value (mathematics); Measure (data warehouse); Harmonic mean; Mathematics; Data mining; Machine learning; Statistics; Combinatorics","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":[0.0001495779,0.0003731039,0.0004041337,0.0001136141,0.0001412127,0.00005436541,0.0006660545,0.001310499,0.0002486611],"category_scores_gemma":[0.000319315,0.0003926255,0.000212363,0.0001823648,0.0005885335,0.000006698304,0.001175569,0.0006534066,0.00004661379],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007156374,"about_ca_system_score_gemma":0.0002763227,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00094062,"about_ca_topic_score_gemma":0.00005138565,"domain_scores_codex":[0.997881,0.0001762042,0.0002726291,0.001116134,0.0001086722,0.0004453812],"domain_scores_gemma":[0.9984683,0.0001077712,0.0003074033,0.0007012369,0.0001394191,0.0002758661],"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":[0.001804058,0.002309132,0.1518489,0.0007683288,0.005996878,0.003005945,0.001495408,0.03321592,0.6815042,0.002942152,0.03029719,0.08481187],"study_design_scores_gemma":[0.01557756,0.001783503,0.0516265,0.002432015,0.0020148,0.000156592,0.006775053,0.6605119,0.04802828,0.03824836,0.1630687,0.009776707],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9441262,0.0005076644,0.05381915,0.00005357225,0.0007114234,0.0001942653,0.00009369227,0.00009006854,0.0004039475],"genre_scores_gemma":[0.9966187,0.0001495188,0.001524434,0.0001329005,0.0005000283,0.000001333975,0.0004381001,0.00003482817,0.0006001836],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.633476,"threshold_uncertainty_score":0.999986,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08242167131080438,"score_gpt":0.2421234274796989,"score_spread":0.1597017561688945,"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."}}