{"id":"W2890999860","doi":"10.23889/ijpds.v3i4.680","title":"Development of a Concept Dictionary to Standardize Definitions and Classifications While Working With a Common Repository of Linked Administrative Data","year":2018,"lang":"en","type":"article","venue":"International Journal for Population Data Science","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Institute for Clinical Evaluative Sciences","funders":"","keywords":"Computer science; Consistency (knowledge bases); Variety (cybernetics); Quality (philosophy); Data science; Key (lock); Information retrieval; World Wide Web; Artificial intelligence","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":[0.06989247,0.001607296,0.001591074,0.01784899,0.004400261,0.0152342,0.005631165,0.003195149,0.01494228],"category_scores_gemma":[0.1113554,0.001582542,0.002168047,0.01367544,0.005721682,0.02429749,0.008692846,0.007232658,0.01271325],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0091643,"about_ca_system_score_gemma":0.03412628,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007047366,"about_ca_topic_score_gemma":0.00541159,"domain_scores_codex":[0.947363,0.01885428,0.01579411,0.003581651,0.01317101,0.001236039],"domain_scores_gemma":[0.8401112,0.04100314,0.0159944,0.02033808,0.07727841,0.005274712],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00014802,0.0002978506,0.003305187,0.003602378,0.00005020428,0.0004753008,0.01133685,0.002107294,0.00417807,0.3027655,0.2423108,0.4294225],"study_design_scores_gemma":[0.00004975204,0.00008565481,0.001278914,0.003043083,0.00002569118,0.0004503018,0.002785,0.002556593,0.002403259,0.03701052,0.9501808,0.0001303684],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00859814,0.002280678,0.875221,0.02844452,0.00708114,0.01366632,0.01008531,0.005359466,0.04926353],"genre_scores_gemma":[0.009769039,0.001462649,0.959085,0.00231165,0.0006286222,0.006703218,0.008651469,0.001249966,0.01013838],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.06989247,"threshold_uncertainty_score":0.3696312,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2714978061344933,"score_gpt":0.4150943451276689,"score_spread":0.1435965389931756,"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."}}