{"id":"W2140162241","doi":"10.1007/s11192-011-0589-1","title":"Author disambiguation using multi-aspect similarity indicators","year":2011,"lang":"en","type":"article","venue":"Scientometrics","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":48,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Social Sciences and Humanities Research Council of Canada; Genome Canada","keywords":"Similarity (geometry); Recall; Precision and recall; Computer science; Task (project management); Measure (data warehouse); Information retrieval; Key (lock); Data mining; Artificial intelligence; Natural language processing; Psychology; Cognitive psychology","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":["bibliometrics"],"consensus_categories":[],"category_scores_codex":[0.001450396,0.000154435,0.0001825386,0.005632685,0.0002468751,0.0001707102,0.001437407,0.00009159531,0.00002730618],"category_scores_gemma":[0.0009301903,0.0001457812,0.0001027673,0.0292352,0.0001241912,0.00112845,0.0005025721,0.0001777672,0.00003255807],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002435515,"about_ca_system_score_gemma":0.00008151416,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007318229,"about_ca_topic_score_gemma":0.00001171848,"domain_scores_codex":[0.9977328,0.00007072586,0.0003002518,0.0005834282,0.0009090232,0.0004037952],"domain_scores_gemma":[0.9984842,0.00006259727,0.0002368593,0.0008169024,0.0001971705,0.0002023053],"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":[0.000009446847,0.001864625,0.3969854,0.00004410848,0.0001100204,0.00007000408,0.01015378,0.0002472493,0.008101798,0.125403,0.0006532187,0.4563573],"study_design_scores_gemma":[0.0005977476,0.0001790324,0.3545432,0.00002753197,0.00007081143,0.00001526575,0.0001162244,0.5287514,0.09066588,0.02152439,0.002424808,0.001083638],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06664888,0.00007596157,0.9314774,0.00003842164,0.0002942264,0.0001413117,0.000002071367,0.0004454151,0.0008762671],"genre_scores_gemma":[0.5548025,0.000003072061,0.4450245,0.00005052084,0.00001237458,0.000003334687,0.000001051423,0.00000629034,0.00009630904],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5285042,"threshold_uncertainty_score":0.9913989,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2003679371428773,"score_gpt":0.3850923397812263,"score_spread":0.184724402638349,"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."}}