{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004522829,0.0009769519,0.001117329,0.009762617,0.002671763,0.003437728,0.002854788,0.00159893,0.00515474],"category_scores_gemma":[0.03074718,0.0006170854,0.001221746,0.009790415,0.001014259,0.00448939,0.002476831,0.001082144,0.003237328],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001365741,"about_ca_system_score_gemma":0.002673831,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007370743,"about_ca_topic_score_gemma":0.01124821,"domain_scores_codex":[0.9955101,0.001192467,0.0005439165,0.0009486539,0.001505299,0.0002996465],"domain_scores_gemma":[0.9846216,0.005131258,0.001264104,0.004252381,0.004229154,0.0005013848],"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":[0.000309534,0.0004068119,0.01280597,0.000366878,0.0001624432,0.0003509684,0.002159715,0.072322,0.009270106,0.06271056,0.02135429,0.8177807],"study_design_scores_gemma":[0.0002429624,0.0002800398,0.007857788,0.0001691905,0.0002261061,0.00144356,0.00337793,0.7360916,0.03171623,0.1426407,0.07563309,0.0003209304],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03455909,0.0002557484,0.9537228,0.0003177308,0.00008519651,0.0006412729,0.001091083,0.003843167,0.00548381],"genre_scores_gemma":[0.1275755,0.0001773853,0.865378,0.00007128308,0.00005275479,0.000483394,0.003186995,0.0004839521,0.002590806],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.009762617,"threshold_uncertainty_score":0.02391928,"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."}}