{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00108115,0.0001158011,0.0002434329,0.00007607163,0.0001458248,0.0002697757,0.0001710852,0.0001639072,0.00002291295],"category_scores_gemma":[0.002171441,0.00009245123,0.00003763245,0.00009777604,0.0001880163,0.0009278167,0.0002568934,0.0002284052,0.00000478016],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000009200686,"about_ca_system_score_gemma":0.0001031307,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001781033,"about_ca_topic_score_gemma":0.00000311195,"domain_scores_codex":[0.9982083,0.00005345198,0.0009025538,0.0002512909,0.0004292978,0.00015512],"domain_scores_gemma":[0.9970749,0.002029294,0.0002056841,0.0001486276,0.000149464,0.0003920532],"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":[0.000071287,0.00001872717,0.0008840655,0.00005661973,0.0000081276,0.000001961733,0.0008802144,0.000002138355,0.000002409538,0.002123791,0.0002184849,0.9957322],"study_design_scores_gemma":[0.001288477,0.0002219167,0.001048963,0.00021401,0.00001139676,0.0001887728,0.001372124,0.9830695,0.000004199409,0.0103796,0.00206235,0.0001387085],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.2908826,0.00006106035,0.7083214,0.0002319223,0.0002740661,0.0001566593,0.000004435787,0.00003868146,0.00002918759],"genre_scores_gemma":[0.1751566,0.000298146,0.8222702,0.002059214,0.0001943393,0.00001038177,0.000005536192,0.000004774062,8.602464e-7],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9955935,"threshold_uncertainty_score":0.3770052,"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."}}