{"id":"W3094834348","doi":"10.2196/23375","title":"The 2019 n2c2/OHNLP Track on Clinical Semantic Textual Similarity: Overview","year":2020,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Topic Modeling","field":"Computer Science","cited_by":59,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Center for Advancing Translational Sciences; U.S. National Library of Medicine","keywords":"Computer science; Automatic summarization; Natural language processing; Information retrieval; Semantic similarity; Artificial intelligence; Task (project management); Unified Medical Language System; Semantics (computer science); Sentence; Similarity (geometry); Set (abstract data type); Semantic computing; Semantic Web","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001405396,0.0001829357,0.0003256169,0.00002754711,0.0001876505,0.0002374436,0.002024564,0.0002405637,0.00006284999],"category_scores_gemma":[0.0008776225,0.0001157863,0.000163674,0.000282576,0.0001573955,0.000410408,0.0006216339,0.001001861,0.0008788631],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002325889,"about_ca_system_score_gemma":0.0002733266,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004268818,"about_ca_topic_score_gemma":0.00000458922,"domain_scores_codex":[0.9966176,0.0001297446,0.001242392,0.0002004321,0.001391471,0.0004184119],"domain_scores_gemma":[0.9974831,0.0008739827,0.0002247125,0.0007596671,0.00006396767,0.000594513],"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":[0.0000218655,0.0001671204,0.0002894692,0.0002044341,0.00006379464,0.00004533878,0.006091048,0.0001184373,7.332204e-7,0.1396086,0.1276946,0.7256945],"study_design_scores_gemma":[0.0005500134,0.0002549833,0.0003576007,0.0001001336,0.000007658233,0.00001441922,0.0002261423,0.7950422,0.000007192638,0.0008304603,0.2024253,0.0001838199],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04309419,0.0006638029,0.7643436,0.1701874,0.002232953,0.001347218,0.00001356087,0.0009471651,0.01717008],"genre_scores_gemma":[0.6544529,0.003187918,0.04734225,0.2910715,0.003113416,0.00008314206,0.00002926492,0.00006080821,0.0006587794],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7949238,"threshold_uncertainty_score":0.9998991,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09220643652773049,"score_gpt":0.3689164150421732,"score_spread":0.2767099785144427,"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."}}