{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001408157,0.001039575,0.0009627531,0.02513953,0.001073436,0.001920405,0.0008101456,0.001264176,0.002251777],"category_scores_gemma":[0.009793296,0.0002726252,0.001070901,0.01028548,0.0006167076,0.003127816,0.001470676,0.0007954611,0.001334381],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007648082,"about_ca_system_score_gemma":0.001215522,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002523335,"about_ca_topic_score_gemma":0.003114977,"domain_scores_codex":[0.9986191,0.0001487438,0.0002276741,0.0003766846,0.0005066866,0.0001211184],"domain_scores_gemma":[0.9946352,0.002789902,0.0009382457,0.0004068994,0.000939549,0.0002902681],"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":[0.0009939799,0.0003934115,0.06081003,0.002347238,0.0004822566,0.002176238,0.002300434,0.007222192,0.05832085,0.01083939,0.02513294,0.828981],"study_design_scores_gemma":[0.000263812,0.00102645,0.2512031,0.000664859,0.001105981,0.005398723,0.00329998,0.4387024,0.07132772,0.1227354,0.103822,0.0004495788],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.4338149,0.008185676,0.502085,0.001501616,0.0006117999,0.001413783,0.02544829,0.01205011,0.01488897],"genre_scores_gemma":[0.5883323,0.001765431,0.3819892,0.0002829737,0.0007299975,0.0006189886,0.0234764,0.0003185064,0.002486203],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.02513953,"threshold_uncertainty_score":0.007532954,"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."}}