{"id":"W2405050116","doi":"10.1016/j.jval.2016.03.1777","title":"PROBABILISTIC RECORD MATCHING USING MACHINE LEARNING TECHNIQUES","year":2016,"lang":"en","type":"article","venue":"Value in Health","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Western University","funders":"","keywords":"Computer science; Matching (statistics); Data mining; Weighting; Confusion matrix; Set (abstract data type); Metric (unit); Probabilistic logic; Levenshtein distance; Artificial intelligence; Algorithm; Mathematics; Statistics","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01259295,0.0001052218,0.0002652371,0.0003161044,0.0001642074,0.000104502,0.0004748017,0.00003929534,0.000144127],"category_scores_gemma":[0.003073136,0.00006522894,0.00004156864,0.0004826433,0.00005035444,0.0003469094,0.0002571446,0.0001566856,0.0001064849],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000244161,"about_ca_system_score_gemma":0.0001172351,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01365038,"about_ca_topic_score_gemma":0.0005602226,"domain_scores_codex":[0.9965158,0.001171774,0.0008705731,0.0004441828,0.0006529336,0.0003447385],"domain_scores_gemma":[0.9977375,0.001328517,0.0003268602,0.0004606414,0.00004770582,0.00009882032],"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":[0.00005262611,0.0001381653,0.01708097,0.0001749832,0.000007138114,0.00001700163,0.001437368,0.002310106,0.0006299536,0.05519828,0.001037155,0.9219162],"study_design_scores_gemma":[0.0005074922,0.0003391576,0.002563301,0.001126014,0.000004699124,0.00001318947,0.0007146866,0.02480981,0.0002675327,0.6228152,0.34644,0.0003989084],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6702071,0.0004620007,0.3003803,0.0225804,0.001018146,0.001633881,0.00006866975,0.0004647977,0.003184721],"genre_scores_gemma":[0.897252,0.0003569664,0.09778221,0.001690254,0.0001766817,0.00003216427,0.00000604266,0.00003451803,0.00266913],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9215173,"threshold_uncertainty_score":0.9929178,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3116090154795184,"score_gpt":0.451216637542168,"score_spread":0.1396076220626496,"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."}}