{"id":"W4241632110","doi":"10.23889/ijpds.v4i2.1133","title":"Population Data BC: Supporting population data science in British Columbia","year":2020,"lang":"en","type":"article","venue":"International Journal for Population Data Science","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":30,"is_retracted":false,"has_abstract":true,"ca_institutions":"The Quebec Population Health Research Network; University of British Columbia","funders":"","keywords":"Computer science; Data access; Linkage (software); Variety (cybernetics); Data quality; Identifier; Data science; Data management; Linked data; Record linkage; Population; Database; World Wide Web; Service (business); Business","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","sts","scholarly_communication","open_science"],"consensus_categories":["scholarly_communication","open_science"],"category_scores_codex":[0.02786832,0.0001851004,0.0003786746,0.0007195481,0.001369474,0.01266832,0.0282646,0.00007032599,0.0004248983],"category_scores_gemma":[0.04174124,0.0002335582,0.00005093791,0.003016863,0.0003963596,0.04263052,0.01163821,0.0003537286,0.00006007649],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003552661,"about_ca_system_score_gemma":0.0004666633,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.05802133,"about_ca_topic_score_gemma":0.1004933,"domain_scores_codex":[0.9874048,0.0001968373,0.002374241,0.002528181,0.006818634,0.0006773034],"domain_scores_gemma":[0.9926067,0.0004740238,0.001676288,0.003634226,0.001158315,0.0004504235],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00004727931,0.0001217217,0.7225228,0.00001209862,0.00001622124,0.0000354007,0.0001483684,0.001601683,0.0001611422,0.001942254,0.03359865,0.2397924],"study_design_scores_gemma":[0.0004827271,0.00002914023,0.6200442,0.00005824766,0.00001440286,0.00004048931,0.0003823851,0.3510511,0.000002042124,0.006311758,0.02135219,0.0002313643],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8865519,0.00005963616,0.07598428,0.01256261,0.009467637,0.001282243,0.01360417,0.0001284257,0.0003591086],"genre_scores_gemma":[0.9646276,0.00004099073,0.01679803,0.001056241,0.0007358834,0.000004779165,0.01654906,0.00001757319,0.0001699069],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3494494,"threshold_uncertainty_score":0.9999306,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4131892460550775,"score_gpt":0.5216265395244426,"score_spread":0.1084372934693651,"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."}}