{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004137367,0.001182597,0.0006683058,0.01888312,0.005259944,0.003885412,0.002361469,0.0006177253,0.02507863],"category_scores_gemma":[0.0229189,0.0006161025,0.0009116135,0.04748207,0.0007879107,0.001225027,0.003218631,0.001282863,0.005769602],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.03970723,"about_ca_system_score_gemma":0.1042809,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.9914972,"about_ca_topic_score_gemma":0.9945961,"domain_scores_codex":[0.9935127,0.0003944461,0.000417541,0.0008435921,0.004097149,0.0007345952],"domain_scores_gemma":[0.9767616,0.0009624159,0.001234706,0.001818804,0.01844399,0.000778581],"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":[0.0001313894,0.00006035327,0.09718855,0.001754464,0.0003316803,0.0002403654,0.004986085,0.002357192,0.000817385,0.01900383,0.5866658,0.2864628],"study_design_scores_gemma":[0.00001730008,0.00001026857,0.1479869,0.0006331608,0.00007979811,0.00009254871,0.002094275,0.001060348,0.0006974723,0.001599101,0.8456356,0.00009326444],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"empirical","genre_scores_codex":[0.02377743,0.004355046,0.01149421,0.002662872,0.0009301399,0.001151656,0.8856658,0.001456848,0.06850588],"genre_scores_gemma":[0.1542272,0.007160305,0.05987854,0.001120225,0.0002519246,0.002159297,0.7085027,0.0009765001,0.06572345],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.03970723,"threshold_uncertainty_score":0.2880974,"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."}}