{"id":"W2890268673","doi":"10.23889/ijpds.v3i4.1034","title":"A New Standards-based Grammar for Linking Aggregate Datasets","year":2018,"lang":"en","type":"article","venue":"International Journal for Population Data Science","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Session (web analytics); Government (linguistics); Interoperability; Aggregate data; Computer science; Human immunodeficiency virus (HIV); Data science; World Wide Web; Medicine; Family medicine","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.0168174,0.0001265289,0.0001627776,0.0006640878,0.0008986755,0.003042957,0.00720956,0.00003512021,0.0002361547],"category_scores_gemma":[0.01359066,0.00009981559,0.00008018828,0.0006112368,0.0002352058,0.005360054,0.0008854617,0.00009613117,0.00004193466],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002019397,"about_ca_system_score_gemma":0.000727983,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001598126,"about_ca_topic_score_gemma":0.0005095854,"domain_scores_codex":[0.9938397,0.00005998301,0.0008578913,0.0007237566,0.004183513,0.0003351378],"domain_scores_gemma":[0.994937,0.0006061639,0.0007311322,0.001126116,0.002354491,0.000245076],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0004034147,0.00005263468,0.00144397,0.000005231655,0.00003464453,0.000004382603,0.0000940235,0.0003931406,0.0002382198,0.04406029,0.3766991,0.5765709],"study_design_scores_gemma":[0.0009171586,0.0001121398,0.001844081,0.00005280456,0.00001435132,0.00001350519,0.00005880491,0.07149269,0.0002504269,0.07436355,0.8507395,0.0001409832],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002406347,0.00001996912,0.9708669,0.005157493,0.006368364,0.0003566308,0.01466355,0.00002534284,0.0001354581],"genre_scores_gemma":[0.5209284,0.00002605804,0.454203,0.004531107,0.005474741,0.00002254444,0.01334377,0.00003281255,0.001437504],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.57643,"threshold_uncertainty_score":0.9981619,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2856651451075076,"score_gpt":0.5436897848150035,"score_spread":0.2580246397074959,"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."}}