{"id":"W3112648112","doi":"10.1186/s12911-020-01330-8","title":"CERC: an interactive content extraction, recognition, and construction tool for clinical and biomedical text","year":2020,"lang":"en","type":"article","venue":"BMC Medical Informatics and Decision Making","topic":"Topic Modeling","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Canada Excellence Research Chairs, Government of Canada; Georgia Institute of Technology; National Science Foundation","keywords":"Automatic summarization; Computer science; Relevance (law); Natural language processing; Artificial intelligence; Ranking (information retrieval); Visualization; Information retrieval; Test set; Multi-document summarization; Vocabulary; Set (abstract data type); Random forest","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00484872,0.002575146,0.001005904,0.008529502,0.0006929051,0.001615683,0.001765106,0.001387748,0.01628097],"category_scores_gemma":[0.01768502,0.0006229405,0.001223748,0.002788204,0.000556118,0.002694878,0.002215802,0.001063165,0.008522968],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007335757,"about_ca_system_score_gemma":0.001711496,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00188224,"about_ca_topic_score_gemma":0.002962357,"domain_scores_codex":[0.9979353,0.0005616344,0.0002458665,0.0004759945,0.0006868765,0.00009436481],"domain_scores_gemma":[0.9835191,0.0107478,0.001722045,0.001075128,0.002466549,0.0004691945],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0008730385,0.0002162926,0.003326488,0.002112903,0.0002673607,0.001013473,0.001183353,0.005121855,0.03895284,0.002217713,0.2147142,0.7300005],"study_design_scores_gemma":[0.001134946,0.001183427,0.02576927,0.001117929,0.0005514173,0.004798783,0.001258932,0.4918659,0.1496077,0.02123614,0.3007692,0.0007063895],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01506097,0.0009002992,0.5717866,0.0008812349,0.0001870421,0.001490667,0.01988609,0.3865477,0.003259315],"genre_scores_gemma":[0.04738561,0.0004203038,0.9088655,0.0004453848,0.0002270196,0.001835583,0.03097651,0.006456084,0.003387983],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01628097,"threshold_uncertainty_score":0.05446529,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2134912446600884,"score_gpt":0.4023797459099472,"score_spread":0.1888885012498588,"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."}}