{"id":"W4237720795","doi":"10.1002/(sici)1097-4571(2000)51:8<774::aid-asi90>3.0.co;2-p","title":"Using clustering strategies for creating authority files","year":2000,"lang":"en","type":"article","venue":"Journal of the American Society for Information Science","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":29,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Research Council Canada; Smithsonian Astrophysical Observatory; National Aeronautics and Space Administration; National Radio Astronomy Observatory; National Science Foundation","keywords":"Computer science; String (physics); Matching (statistics); Word (group theory); Information retrieval; Cluster analysis; Categorization; Spelling; String searching algorithm; Quality (philosophy); Metadata; Data mining; Artificial intelligence; Pattern matching; World Wide Web","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":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.01030636,0.00007940277,0.0002126298,0.0001048126,0.001007594,0.001281567,0.001554268,0.00001489217,0.00002896343],"category_scores_gemma":[0.001589766,0.00004755428,0.0004486957,0.001351072,0.0007466259,0.007820426,0.0001506284,0.00009097887,0.000004491732],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001156267,"about_ca_system_score_gemma":0.0003865179,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003617692,"about_ca_topic_score_gemma":0.000003285327,"domain_scores_codex":[0.9973643,0.00003839719,0.0008768938,0.0001039535,0.001381497,0.0002349476],"domain_scores_gemma":[0.9965649,0.0006096166,0.001639066,0.000299343,0.000814749,0.00007233069],"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":[0.0002163084,0.00005371288,0.0002957682,0.00006780053,0.00007261847,1.061788e-7,0.02706285,0.1411899,0.001979192,0.0170259,0.03865014,0.7733857],"study_design_scores_gemma":[0.0006798728,0.000283612,0.00456704,0.00006927901,0.00005603644,0.00003075114,0.1509972,0.4814226,0.0004310828,0.01972359,0.3414936,0.0002453065],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3320829,0.00000841731,0.6633872,0.001331517,0.0003878165,0.000319364,0.00007986581,0.00001085129,0.002392088],"genre_scores_gemma":[0.7843632,0.00002151851,0.2122412,0.002933534,0.0001616904,0.000007075422,0.00000136356,0.000004094033,0.0002664139],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7731404,"threshold_uncertainty_score":0.9997552,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1914334805385595,"score_gpt":0.4529099753684113,"score_spread":0.2614764948298517,"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."}}