{"id":"W2565966619","doi":"10.1109/cbi.2016.9","title":"ELM: An Extended Logic Matching Method on Record Linkage Analysis of Disparate Databases for Profiling Data Mining","year":2016,"lang":"en","type":"article","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dalhousie University","funders":"","keywords":"Computer science; Data mining; Probabilistic logic; Profiling (computer programming); Data deduplication; Matching (statistics); Identifier; Artificial intelligence; Machine learning; Database; 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":[0.01445403,0.0001632156,0.0005591598,0.0006234299,0.0001467001,0.0001722611,0.002116387,0.00003661717,0.0006026712],"category_scores_gemma":[0.00433847,0.00008673939,0.0001270012,0.001030294,0.00005514625,0.001569147,0.001011649,0.0000474353,0.00004032965],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001554537,"about_ca_system_score_gemma":0.00003045295,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001684928,"about_ca_topic_score_gemma":0.001000772,"domain_scores_codex":[0.9962002,0.0005968623,0.0009622043,0.00113372,0.0008182005,0.000288783],"domain_scores_gemma":[0.9900693,0.005924895,0.0004959488,0.003257714,0.0001458634,0.0001062944],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002743911,0.0003254108,0.001133154,0.00003301772,0.0006164503,0.000005295129,0.0002261532,0.0003025873,0.005093668,0.09271865,0.007908868,0.8913624],"study_design_scores_gemma":[0.004317333,0.001779483,0.02105179,0.0004838775,0.004864139,0.000002977034,0.03032524,0.5078593,0.03529191,0.2058508,0.1856213,0.002551902],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03621249,0.00001321201,0.9583755,0.0007335524,0.0001642766,0.0003093855,0.002757166,0.0000460598,0.00138838],"genre_scores_gemma":[0.07077489,0.00003027105,0.9236903,0.0007720756,0.00006202854,0.00002504676,0.001093196,0.0000124951,0.003539652],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8888105,"threshold_uncertainty_score":0.6598828,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.5979240502219576,"score_gpt":0.5597760552806768,"score_spread":0.03814799494128085,"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."}}