{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004357191,0.00005215539,0.00007701332,0.00008151308,0.0002679303,0.000042777,0.0007778979,0.00003168103,0.000002573885],"category_scores_gemma":[0.0003279177,0.0000424745,0.000009246309,0.000117673,0.0004980231,0.00003867254,0.0003432664,0.00004363487,1.308218e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002104972,"about_ca_system_score_gemma":0.0003520301,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009981641,"about_ca_topic_score_gemma":0.00009931671,"domain_scores_codex":[0.9990536,0.00001659413,0.0002958273,0.0002403318,0.0003154336,0.00007823687],"domain_scores_gemma":[0.9989004,0.00003786,0.0002311629,0.0003227014,0.0004435719,0.00006429052],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.002401078,0.0007338141,0.1288016,0.00003918726,0.0007581203,0.00000728147,0.005284531,0.0001654988,0.4946229,0.008959952,0.008792742,0.3494333],"study_design_scores_gemma":[0.002630767,0.002375689,0.5756494,0.0008522004,0.0001182601,0.0005080592,0.004121237,0.008152263,0.09892697,0.0008800488,0.3051556,0.0006294722],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8405918,0.0001018104,0.1563792,0.0006880647,0.0005407024,0.0001789968,0.001212089,0.000007696283,0.0002995536],"genre_scores_gemma":[0.8627594,0.00000895928,0.1363108,0.00003129788,0.0001213208,0.000003885028,0.0007455411,0.000002780517,0.00001604419],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4468478,"threshold_uncertainty_score":0.206073,"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."}}