{"id":"W2148524305","doi":"10.14778/1687627.1687771","title":"Framework for evaluating clustering algorithms in duplicate detection","year":2009,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":232,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Scalability; Cluster analysis; Data mining; Data deduplication; Process (computing); Algorithm; Machine learning; Database","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.05879213,0.002601526,0.002919211,0.01180054,0.002354739,0.005690672,0.005376305,0.00425544,0.001794421],"category_scores_gemma":[0.1066421,0.0008347164,0.002408877,0.009012589,0.002695965,0.00483065,0.005912534,0.002610947,0.0008506694],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.004568572,"about_ca_system_score_gemma":0.004954954,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007920526,"about_ca_topic_score_gemma":0.005157467,"domain_scores_codex":[0.9419968,0.03202862,0.004135181,0.003337024,0.01725783,0.001244553],"domain_scores_gemma":[0.9364167,0.03646897,0.005568864,0.008679273,0.01173811,0.001128086],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0009888812,0.001387541,0.01325356,0.001273341,0.001211442,0.0002533754,0.0007350098,0.5713453,0.009797089,0.1509697,0.008617209,0.2401675],"study_design_scores_gemma":[0.0001858201,0.001166475,0.002772674,0.0001680039,0.0001923019,0.0002233082,0.0002883164,0.9321498,0.005740625,0.04993129,0.007071983,0.0001093278],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02810548,0.001398938,0.9589446,0.0006685856,0.0001231674,0.00202075,0.0008784202,0.001899018,0.005961181],"genre_scores_gemma":[0.1118798,0.000395148,0.8841136,0.0001743555,0.00007874138,0.001652139,0.0008694024,0.0001627496,0.000674109],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.05879213,"threshold_uncertainty_score":0.3109262,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2418184006816228,"score_gpt":0.4629068859449667,"score_spread":0.2210884852633439,"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."}}