{"id":"W4293243715","doi":"10.23889/ijpds.v7i3.2077","title":"Analysing Siamese Neural Network Architectures for Computing Name Similarity.","year":2022,"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":"University of Guelph","funders":"","keywords":"Similarity (geometry); Computer science; Classifier (UML); False positive paradox; Artificial intelligence; String metric; Artificial neural network; Random forest; Similitude; False positives and false negatives; Set (abstract data type); Machine learning; Pattern recognition (psychology); Data mining; String searching algorithm; Pattern matching","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003646617,0.0006867042,0.0004978708,0.001571099,0.0005392871,0.001044737,0.001126543,0.0009835815,0.002368027],"category_scores_gemma":[0.01091333,0.0002784496,0.0005982806,0.0009518068,0.0005225866,0.001694719,0.0006869697,0.001192555,0.0004871496],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001941089,"about_ca_system_score_gemma":0.001084261,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0178784,"about_ca_topic_score_gemma":0.01863713,"domain_scores_codex":[0.9993334,0.0002027158,0.00004249569,0.0001367603,0.0002024956,0.00008205707],"domain_scores_gemma":[0.9946647,0.003056335,0.0004067897,0.0003564933,0.001351678,0.0001639918],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000189801,0.0001331635,0.01367384,0.00006390252,0.0001065717,0.0001097832,0.0000842105,0.8601305,0.001818388,0.0103062,0.00241093,0.1109727],"study_design_scores_gemma":[0.000001837637,0.00001245442,0.0003948216,0.000002506373,0.000003444259,0.00000847992,0.000006640717,0.9970273,0.0002547411,0.002199111,0.00008621337,0.000002360119],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.5511438,0.001863214,0.4357111,0.002026601,0.0002421741,0.0002156694,0.0005263764,0.001338443,0.006932647],"genre_scores_gemma":[0.9144423,0.0003720657,0.0800181,0.0002050795,0.00009136471,0.0001177318,0.0008782903,0.00004984221,0.003825166],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.0178784,"threshold_uncertainty_score":0.03554869,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2782177487324201,"score_gpt":0.5106037761682547,"score_spread":0.2323860274358346,"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."}}