{"id":"W2474779893","doi":"10.2196/medinform.5490","title":"A Semi-Supervised Learning Approach to Enhance Health Care Community–Based Question Answering: A Case Study in Alcoholism","year":2016,"lang":"en","type":"preprint","venue":"JMIR Medical Informatics","topic":"Expert finding and Q&A systems","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"U.S. National Library of Medicine","keywords":"Question answering; Computer science; Set (abstract data type); Information retrieval; Unified Medical Language System; Rank (graph theory); Test (biology); Similarity (geometry); Artificial intelligence; Baseline (sea); String metric; Test set; Natural language processing; Machine learning; String searching algorithm; Mathematics","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":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.003638632,0.0004558736,0.0008522879,0.0005499045,0.0004032533,0.0003153918,0.002071332,0.000523766,0.000002793091],"category_scores_gemma":[0.0002812114,0.0003731929,0.0001149457,0.0005303585,0.00006707418,0.0003187456,0.00204024,0.003099787,0.00002970747],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006700073,"about_ca_system_score_gemma":0.001165106,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002368871,"about_ca_topic_score_gemma":0.0003087716,"domain_scores_codex":[0.994552,0.001477808,0.0015519,0.0003683199,0.001377348,0.000672642],"domain_scores_gemma":[0.9967454,0.0002907513,0.0005134871,0.0015586,0.0001807688,0.0007110143],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001520996,0.0008370149,0.001152241,0.003289491,0.00003701063,0.0002779249,0.9421045,0.002415196,0.000003079504,0.000216523,0.0009542325,0.0486976],"study_design_scores_gemma":[0.002841217,0.001436503,0.0002792183,0.009222236,0.00001333486,0.0008499394,0.1769987,0.8013652,0.00005378619,0.00006332194,0.005266833,0.001609736],"study_design_candidate":"qualitative","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.518221,0.0001180648,0.4755847,0.0007417692,0.0006448593,0.002432631,0.000009283626,0.0004993842,0.001748319],"genre_scores_gemma":[0.9813144,0.00000878649,0.01590789,0.001619437,0.0001439469,0.0008837205,0.00005345551,0.00002742918,0.00004091645],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.79895,"threshold_uncertainty_score":0.999872,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04537685676127573,"score_gpt":0.37189076878779,"score_spread":0.3265139120265143,"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."}}