{"id":"W2111094784","doi":"10.1109/iccit.2008.210","title":"Social Network Analysis on Name Disambiguation and More","year":2008,"lang":"en","type":"article","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Disk formatting; String metric; Social network analysis; Information retrieval; Similarity (geometry); String (physics); Correct name; Social network (sociolinguistics); Natural language processing; Graph; World Wide Web; Artificial intelligence; String searching algorithm; Social media; Theoretical computer science; Pattern matching; Mathematics","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":[0.001228129,0.00005268533,0.0001451547,0.0001206693,0.0002830509,0.00009623824,0.0001842175,0.00002498731,0.0005083519],"category_scores_gemma":[0.0002124217,0.00003630235,0.00006703829,0.000899886,0.00008210721,0.0001690831,0.0001008175,0.00003396386,0.0001893575],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000009068522,"about_ca_system_score_gemma":0.000005593671,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007944344,"about_ca_topic_score_gemma":0.0001475444,"domain_scores_codex":[0.9986181,0.00009659302,0.0002197335,0.0002509606,0.000704839,0.0001098289],"domain_scores_gemma":[0.9993876,0.0002315112,0.00006675044,0.0002277369,0.00004973261,0.00003663029],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"observational","study_design_scores_codex":[0.00004711072,0.0001130069,0.04067848,0.000001939961,0.0002727789,0.00001131838,0.002304839,0.002968048,0.00000189386,0.1886431,0.6400792,0.1248783],"study_design_scores_gemma":[0.000243107,0.00004309722,0.815884,0.000001198821,0.0001152771,6.553122e-7,0.00127335,0.009447567,0.000005723699,0.03949694,0.1333323,0.0001567368],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8499382,0.00003454602,0.08669509,0.01296471,0.0001675491,0.0001491676,0.00001736443,0.00006745855,0.04996594],"genre_scores_gemma":[0.9893189,0.00001362545,0.0005489985,0.001740471,0.00009438241,0.000002830674,0.00002178659,0.000001701293,0.008257282],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7752055,"threshold_uncertainty_score":0.5566097,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2179606429412178,"score_gpt":0.4426846600958866,"score_spread":0.2247240171546688,"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."}}