{"id":"W2610937402","doi":"10.2196/publichealth.6396","title":"TwiMed: Twitter and PubMed Comparable Corpus of Drugs, Diseases, Symptoms, and Their Relations","year":2017,"lang":"en","type":"article","venue":"JMIR Public Health and Surveillance","topic":"Pharmacovigilance and Adverse Drug Reactions","field":"Pharmacology, Toxicology and Pharmaceutics","cited_by":82,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Engineering and Physical Sciences Research Council; Ministry of Education, Culture, Sports, Science and Technology","keywords":"Annotation; Pharmacovigilance; Computer science; Set (abstract data type); Information retrieval; Natural language processing; Resource (disambiguation); Artificial intelligence; Data science; Medicine; Drug","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008361771,0.000202375,0.0004380849,0.0001016749,0.001052776,0.00009104389,0.0001724313,0.0001370495,0.00005741624],"category_scores_gemma":[0.0001338728,0.0001744062,0.00004107609,0.00008866628,0.0005541324,0.0003654698,0.0001181233,0.0004467905,0.000006262399],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004009424,"about_ca_system_score_gemma":0.0002686954,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008593275,"about_ca_topic_score_gemma":0.00003445272,"domain_scores_codex":[0.9983016,0.0003127488,0.0003568127,0.0003414035,0.00009910879,0.0005883008],"domain_scores_gemma":[0.997853,0.0004084207,0.0003642981,0.0002977551,0.00007978023,0.0009967777],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00008777946,0.000159763,0.9287818,0.0001666004,0.00009186022,0.000002924857,0.001081532,0.000003247703,0.00009601744,0.0007928025,0.01075092,0.05798477],"study_design_scores_gemma":[0.001505248,0.00003908575,0.5167977,0.000008538033,0.000004064061,0.00001880872,0.0002444608,0.001019666,0.00001592672,0.0001900378,0.4799961,0.0001604457],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9736701,0.006234276,0.00001964889,0.01471708,0.0004664349,0.0006772431,0.0003264784,0.00006529139,0.003823486],"genre_scores_gemma":[0.9915205,0.004050641,0.00001352833,0.003200129,0.000133951,0.0001518456,0.00006025375,0.0000145726,0.0008545604],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4692452,"threshold_uncertainty_score":0.8097211,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.110992696657757,"score_gpt":0.4170413079632729,"score_spread":0.3060486113055159,"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."}}