{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","sts","scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.0198633,0.000120445,0.00018588,0.0001312678,0.004261568,0.00220666,0.01978851,0.00003855733,0.0002321499],"category_scores_gemma":[0.0245524,0.0000822382,0.00003798387,0.00008162046,0.0004185512,0.003102659,0.006275942,0.0001529842,0.00001812446],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003294981,"about_ca_system_score_gemma":0.0004274934,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.03964978,"about_ca_topic_score_gemma":0.2444031,"domain_scores_codex":[0.9953352,0.0001620674,0.0008274852,0.000740368,0.002629183,0.0003056724],"domain_scores_gemma":[0.9922515,0.003126693,0.001331417,0.002675648,0.0004985975,0.0001162169],"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":[0.0001155627,0.00003322504,0.003882921,0.000003921773,0.00007218737,0.000008347694,0.0001098789,0.0002736327,0.00007185533,0.02878278,0.5398387,0.426807],"study_design_scores_gemma":[0.0003982527,0.00002130146,0.07674168,0.00000584961,0.00003194342,0.00001401387,0.0002218597,0.06100624,0.00001362185,0.02093741,0.8404877,0.000120177],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.003124041,0.000027883,0.9253559,0.02320576,0.009652668,0.0004130856,0.03812001,0.000006268326,0.00009443123],"genre_scores_gemma":[0.399483,0.0004680867,0.5594035,0.005472804,0.005795038,0.00006052488,0.01774929,0.00004483543,0.01152288],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4266868,"threshold_uncertainty_score":0.9988291,"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."}}