{"id":"W2017217509","doi":"10.1007/s10115-011-0397-1","title":"Scalable clustering methods for the name disambiguation problem","year":2011,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":23,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"University of Illinois at Urbana-Champaign; University of British Columbia; Advanced Digital Sciences Center; Pennsylvania State University; National Science Foundation","keywords":"Cluster analysis; Computer science; Scalability; Artificial intelligence; Natural language processing; Entity linking; Data mining; Database","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":[],"consensus_categories":[],"category_scores_codex":[0.008740007,0.00008212918,0.0001491528,0.0001302008,0.000302446,0.000546005,0.0003521977,0.00004326124,0.00004269716],"category_scores_gemma":[0.0005829246,0.00004699517,0.00004276058,0.0002524482,0.00004280791,0.003275534,0.0001721007,0.00004190734,0.0003713012],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001980986,"about_ca_system_score_gemma":0.00001989503,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008203866,"about_ca_topic_score_gemma":0.00002159074,"domain_scores_codex":[0.9986074,0.0001951491,0.0007045777,0.0001211589,0.0002313981,0.0001402942],"domain_scores_gemma":[0.9983549,0.000668644,0.0002670132,0.0003420416,0.0003204006,0.00004700798],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00002038821,0.00001623201,0.00008231983,0.0001329863,0.00002104025,1.56923e-8,0.01572614,0.00005586748,0.000004409889,0.09761997,0.02069665,0.865624],"study_design_scores_gemma":[0.0002154554,0.000033797,0.0006820714,0.00002184191,0.00001163526,0.000001865895,0.005581904,0.1243545,0.00003541122,0.002260976,0.8667283,0.00007222288],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0001293776,0.000703313,0.9004654,0.0001318237,0.0007820256,0.0007959562,0.00001585072,0.00003346075,0.09694281],"genre_scores_gemma":[0.9021753,0.0004080944,0.0719536,0.0008394708,0.0004590142,0.0016313,0.0001338732,0.00002423467,0.02237508],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.902046,"threshold_uncertainty_score":0.5265139,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2257578615555757,"score_gpt":0.4321284819533481,"score_spread":0.2063706203977725,"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."}}