{"id":"W3035531049","doi":"10.1145/3397271.3401135","title":"Coding Electronic Health Records with Adversarial Reinforcement Path Generation","year":2020,"lang":"en","type":"article","venue":"","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"National Natural Science Foundation of China; Tencent","keywords":"Computer science; Coding (social sciences); ENCODE; Reinforcement learning; Path (computing); Encoder; Adversarial system; Artificial intelligence; Computer network","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":[0.001899843,0.0008891108,0.0006512105,0.0006116072,0.0003670487,0.0005915321,0.002063087,0.001377825,0.002189173],"category_scores_gemma":[0.009090014,0.0003850442,0.0005844928,0.0005819951,0.000872745,0.001259472,0.00161017,0.002141418,0.0005681558],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001387038,"about_ca_system_score_gemma":0.00131709,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006108634,"about_ca_topic_score_gemma":0.005460885,"domain_scores_codex":[0.9989294,0.000398627,0.00004901286,0.0003063585,0.0002154132,0.0001010355],"domain_scores_gemma":[0.9950345,0.003401696,0.0003205318,0.0006397592,0.0004409532,0.0001626479],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0001989437,0.0001075005,0.002651086,0.00005134746,0.00002950189,0.0001422866,0.00008540923,0.8990216,0.00117258,0.005459228,0.005390419,0.0856901],"study_design_scores_gemma":[0.00001305662,0.00002487777,0.0001082414,0.000004531802,0.000003177568,0.00002138187,0.000005130368,0.9952534,0.0006387246,0.0035018,0.0004215607,0.000004131915],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09423132,0.0006328828,0.8947357,0.001550811,0.000171276,0.0003758247,0.00109402,0.004565611,0.002642476],"genre_scores_gemma":[0.8082781,0.0002379348,0.1830244,0.0006390938,0.00007456004,0.0003386981,0.002508929,0.0001722024,0.004726195],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006108634,"threshold_uncertainty_score":0.01214617,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03366987630125309,"score_gpt":0.2511299121722091,"score_spread":0.217460035870956,"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."}}