{"id":"W2137811660","doi":"10.1140/epjds/s13688-014-0011-3","title":"Exploiting citation networks for large-scale author name disambiguation","year":2014,"lang":"en","type":"article","venue":"EPJ Data Science","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":53,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Metadata; Ranking (information retrieval); Citation; Similarity (geometry); Cluster analysis; Precision and recall; Bibliographic coupling; Parameterized complexity; Heuristics","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","scholarly_communication"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03493439,0.000101746,0.0001564664,0.0002179241,0.000809848,0.001171932,0.003683984,0.00003447188,0.00009560783],"category_scores_gemma":[0.01789395,0.00008225974,0.00003242824,0.001282667,0.0002293966,0.005170112,0.001376951,0.00007587486,0.0002045199],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003367738,"about_ca_system_score_gemma":0.00005842218,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002308111,"about_ca_topic_score_gemma":0.0001291563,"domain_scores_codex":[0.9961376,0.0001733967,0.0005292729,0.001037615,0.001669686,0.0004524335],"domain_scores_gemma":[0.9959365,0.001305184,0.0002857179,0.002050131,0.0002832933,0.0001392325],"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":[0.00003062711,0.0001433539,0.001207938,0.00001758145,0.000005758546,4.933555e-7,0.002202626,0.002575997,0.0007175249,0.2446856,0.09711516,0.6512973],"study_design_scores_gemma":[0.0002086783,0.00003672068,0.005384765,0.00001196134,0.000007094954,4.240794e-7,0.002097685,0.7581882,0.00006551889,0.01925048,0.2146195,0.000129045],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01036611,0.00001603668,0.9838091,0.00236919,0.0009880613,0.0003037958,0.0003242148,0.00005419436,0.001769292],"genre_scores_gemma":[0.9488891,0.000005657101,0.04784369,0.00105235,0.0003214616,0.0000376039,0.0006622946,0.000008421314,0.001179387],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.938523,"threshold_uncertainty_score":0.9998649,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3376502821107572,"score_gpt":0.4681113964519575,"score_spread":0.1304611143412003,"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."}}