{"id":"W4293243843","doi":"10.23889/ijpds.v7i3.2076","title":"Linking Eight Decades of Canadian Census Collections.","year":2022,"lang":"en","type":"article","venue":"International Journal for Population Data Science","topic":"Data Analysis and Archiving","field":"Social Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Guelph","funders":"","keywords":"Census; Data science; Computer science; Leverage (statistics); Population; Record linkage; Demographics; Data quality; Linkage (software); Geography; Data mining; Demography; Machine learning; Sociology; Business; Marketing","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":["sts"],"consensus_categories":[],"category_scores_codex":[0.002982306,0.000043955,0.0000731919,0.001640761,0.004258106,0.0004058959,0.00228874,0.00001152469,0.0002509706],"category_scores_gemma":[0.000883807,0.00004555938,0.00004427512,0.001794257,0.0001650734,0.001318358,0.0003103806,0.0001273007,8.262798e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003665979,"about_ca_system_score_gemma":0.0008624166,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.1133051,"about_ca_topic_score_gemma":0.1567991,"domain_scores_codex":[0.9980882,0.00007543308,0.0002881798,0.0001986643,0.001133378,0.0002161065],"domain_scores_gemma":[0.9989567,0.000104668,0.0002454911,0.000186983,0.000348169,0.0001579734],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00008651612,0.0002304016,0.2338543,0.000008464222,0.0002044163,0.00003008728,0.007354159,0.01503975,0.001827046,0.5245904,0.07610159,0.1406728],"study_design_scores_gemma":[0.000139973,0.00001581612,0.009987113,0.00001412982,0.00001357548,0.00001865809,0.001541446,0.01003521,0.00002306417,0.004650411,0.973474,0.00008665642],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7654631,0.0005452727,0.02266016,0.04714901,0.04161245,0.001639877,0.03550198,0.0001292675,0.08529888],"genre_scores_gemma":[0.9933796,0.00007352231,0.004525535,0.0001370851,0.0003562141,0.000004511235,0.0007228761,0.000004148384,0.0007964979],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8973724,"threshold_uncertainty_score":0.9970382,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09637734138154412,"score_gpt":0.4084209961291392,"score_spread":0.312043654747595,"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."}}