{"id":"W2990325812","doi":"10.23889/ijpds.v4i3.1209","title":"Linked Administrative Data at Statistics Canada – new data resources for horizontal research","year":2019,"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":"Statistics Canada","funders":"","keywords":"Record linkage; Linkage (software); Immigration; Analytics; Data science; Business; Public relations; Geography; Database; Political science; Sociology; Computer science; Law","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","scholarly_communication","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.0221382,0.0001437089,0.0002199523,0.000442493,0.0009378011,0.002506228,0.02710172,0.00004182828,0.0003701182],"category_scores_gemma":[0.02672257,0.0001165457,0.00002127817,0.000679787,0.0002385165,0.007172492,0.01080175,0.0002429981,0.00006374328],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004769858,"about_ca_system_score_gemma":0.002755861,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.07393765,"about_ca_topic_score_gemma":0.4849033,"domain_scores_codex":[0.990311,0.0001801672,0.0010441,0.001439019,0.006553828,0.0004718842],"domain_scores_gemma":[0.9891706,0.003347188,0.0006894989,0.004446929,0.00199081,0.000354971],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0002495709,0.00003887294,0.003403589,0.000005028478,0.00004147277,0.00000787681,0.00009972018,0.0000955518,0.00008991778,0.01716868,0.9315987,0.04720106],"study_design_scores_gemma":[0.0006304268,0.000110258,0.01649333,0.00002664695,0.00001257247,0.00002736153,0.0008409765,0.08805827,0.00001194878,0.01307198,0.8805559,0.0001603583],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"empirical","genre_scores_codex":[0.08807018,0.0001722992,0.3893964,0.02813249,0.02406503,0.003098742,0.4654337,0.00004553005,0.001585559],"genre_scores_gemma":[0.6993898,0.00008885317,0.1599821,0.001267096,0.003222495,0.00001605814,0.1114171,0.00004224172,0.02457434],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6113195,"threshold_uncertainty_score":0.9985293,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.6937162468840304,"score_gpt":0.6065499564550645,"score_spread":0.08716629042896595,"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."}}