{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004422265,0.001548225,0.002923498,0.003684261,0.00202741,0.002369818,0.004323401,0.002242126,0.003866598],"category_scores_gemma":[0.0160442,0.001087826,0.001705097,0.006425919,0.001191119,0.005085086,0.00421585,0.002713499,0.001422555],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001728211,"about_ca_system_score_gemma":0.003514505,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01063374,"about_ca_topic_score_gemma":0.01596277,"domain_scores_codex":[0.9958887,0.001417325,0.0003206194,0.0009394631,0.001154528,0.0002793235],"domain_scores_gemma":[0.9902293,0.005135311,0.000702271,0.002248099,0.001363667,0.0003213358],"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":[0.0004587182,0.0003763997,0.001870492,0.0004820086,0.0004074992,0.0001243349,0.0002579805,0.3377997,0.004516144,0.04367876,0.02886019,0.5811678],"study_design_scores_gemma":[0.0000804997,0.00003216534,0.000441965,0.00002021127,0.00004263174,0.0000474908,0.00005459541,0.9029911,0.0008989739,0.09293938,0.002428419,0.00002256098],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.009259845,0.001336226,0.9852647,0.000619024,0.0001600165,0.00009745931,0.0005225118,0.001625756,0.001114329],"genre_scores_gemma":[0.1552874,0.0009935036,0.8358585,0.0003072194,0.0005553812,0.0003063303,0.003019715,0.0005716212,0.003100267],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01063374,"threshold_uncertainty_score":0.02338743,"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."}}