{"id":"W2606808438","doi":"10.23889/ijpds.v1i1.49","title":"Record Linkage Methodology for the Social Data Linkage Environment at Statistics Canada","year":2017,"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; Probabilistic logic; Linkage (software); Statistic; Computer science; Population; Data science; Data mining; Statistics; Artificial intelligence; Mathematics","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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.03072387,0.001067052,0.001378393,0.009494556,0.004811175,0.007275891,0.003709082,0.001666874,0.03566044],"category_scores_gemma":[0.09420256,0.001358159,0.00189589,0.02360485,0.002048999,0.003366777,0.005394897,0.003481943,0.008426421],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.02361061,"about_ca_system_score_gemma":0.1312315,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.6643257,"about_ca_topic_score_gemma":0.64524,"domain_scores_codex":[0.966649,0.01419714,0.002416006,0.00211079,0.01348833,0.001138823],"domain_scores_gemma":[0.930548,0.01996784,0.00362331,0.008516053,0.03600745,0.0013374],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001316629,0.00008233127,0.007152881,0.0007750407,0.0004237856,0.0003029378,0.001472467,0.02077433,0.0006575107,0.5094249,0.2018385,0.2569637],"study_design_scores_gemma":[0.0001476482,0.00004207471,0.006951348,0.0005991782,0.0001330414,0.0002533066,0.0007367832,0.09423986,0.002099846,0.1758582,0.7187206,0.0002182136],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00162719,0.0006757855,0.95518,0.002655894,0.0002990988,0.0007734257,0.01495399,0.005892094,0.01794246],"genre_scores_gemma":[0.0276756,0.000963811,0.9368312,0.0007461213,0.0001592552,0.00265841,0.01241567,0.001920661,0.01662923],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9763894,"threshold_uncertainty_score":0.6753024,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.6885121311704627,"score_gpt":0.5782337375018265,"score_spread":0.1102783936686362,"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."}}