{"id":"W3017715546","doi":"10.1162/dint_a_00058","title":"The Semantic Data Dictionary – An Approach for Describing and Annotating Data","year":2020,"lang":"en","type":"article","venue":"Data Intelligence","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":49,"is_retracted":false,"has_abstract":true,"ca_institutions":"CARE Canada; Privacy Analytics (Canada)","funders":"National Institute of Environmental Health Sciences","keywords":"Computer science; Natural language processing; Data dictionary; Information retrieval; Artificial intelligence; World Wide Web; Metadata","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":[0.0006288765,0.000100361,0.0000899005,0.000006989841,0.0002559689,0.00008880169,0.002943313,0.00007203253,0.000001490444],"category_scores_gemma":[0.001786921,0.00007213671,0.000007798151,0.00006580591,0.0002396104,0.00002846826,0.003565083,0.00009581059,0.000001584401],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000001521155,"about_ca_system_score_gemma":0.00004350666,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002456848,"about_ca_topic_score_gemma":0.00001774558,"domain_scores_codex":[0.998675,0.0000474742,0.0001815064,0.0008076727,0.0000980488,0.0001903007],"domain_scores_gemma":[0.9974102,0.0001049195,0.00005673081,0.002309199,0.00002812066,0.00009083242],"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":[0.0001168812,0.00005674204,0.0010786,0.00008757353,0.00008999468,0.000003050153,0.000192302,0.00002838982,0.009267421,0.000160715,0.04346825,0.9454501],"study_design_scores_gemma":[0.00009489647,0.0002253617,0.0001493209,0.00001716744,0.00004184507,0.00002564718,0.002287391,0.7125035,0.001492657,0.00007274091,0.2828795,0.0002099846],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005820891,0.004310057,0.983942,0.001306311,0.0001128483,0.0002144352,0.004183926,0.00003595827,0.00007356018],"genre_scores_gemma":[0.6566525,0.002302815,0.2389399,0.001357423,0.0009804609,0.00001998055,0.09966188,0.00003631598,0.00004877497],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9452401,"threshold_uncertainty_score":0.5469457,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3725294609797752,"score_gpt":0.3740642515334556,"score_spread":0.001534790553680387,"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."}}