{"id":"W4402404963","doi":"10.23889/ijpds.v9i5.2624","title":"From Probabilistic to Fuzzy Matching Record Linkage: A promising Transition","year":2024,"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":"","funders":"","keywords":"Probabilistic logic; Matching (statistics); Transition (genetics); Linkage (software); Computer science; Record linkage; Fuzzy logic; Data mining; Artificial intelligence; Mathematics; Biology; Genetics; Statistics; Sociology","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.008973889,0.0001158568,0.0001432282,0.0007802976,0.0004633207,0.005798174,0.003879327,0.00003221971,0.0001721748],"category_scores_gemma":[0.004590677,0.00009166232,0.00007003001,0.0008644378,0.00008288154,0.006713409,0.0006014244,0.0001757274,0.000190028],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000224758,"about_ca_system_score_gemma":0.0001832219,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005538721,"about_ca_topic_score_gemma":0.0002300047,"domain_scores_codex":[0.9953128,0.00009042049,0.0008622272,0.0008333096,0.002666578,0.0002347038],"domain_scores_gemma":[0.9977128,0.0006455926,0.0001958243,0.0006659527,0.0005966003,0.0001832552],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001573645,0.00009672051,0.0002238509,0.00002005972,0.00006496019,0.00004775434,0.003756177,0.008350462,0.002697369,0.04998855,0.0342724,0.9003243],"study_design_scores_gemma":[0.0002735921,0.00006323039,0.005720302,0.0003412433,0.00003023096,0.00004703713,0.000943079,0.1484911,0.00005357081,0.691453,0.1523337,0.0002499561],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1946642,0.00003790429,0.7729481,0.01840427,0.01113871,0.0004731304,0.001915695,0.00007536018,0.0003425917],"genre_scores_gemma":[0.940707,0.000009808396,0.05571961,0.0008955071,0.001510721,0.00001397276,0.0007179431,0.00001235656,0.0004130262],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9000744,"threshold_uncertainty_score":0.9952339,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2454747086708002,"score_gpt":0.5016516879164926,"score_spread":0.2561769792456924,"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."}}