{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005075376,0.0001091063,0.0002029045,0.0001135759,0.0001278313,0.0001587514,0.0008756947,0.00004947625,0.00001426738],"category_scores_gemma":[0.002896374,0.00007238074,0.0001082241,0.0005809948,0.00003186712,0.000297467,0.000285715,0.000116083,0.000009187585],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008238278,"about_ca_system_score_gemma":0.000007840089,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002863098,"about_ca_topic_score_gemma":0.0000124774,"domain_scores_codex":[0.9978746,0.00001702597,0.000615692,0.0003701682,0.0008803767,0.0002421305],"domain_scores_gemma":[0.9988445,0.000290364,0.0004058883,0.0002213299,0.0001998074,0.00003808988],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001424575,0.0001694117,0.0004795575,0.0000515358,0.00001755442,1.209039e-7,0.001515742,0.0005510604,0.02940103,0.02867866,0.0007374,0.9382555],"study_design_scores_gemma":[0.0009947035,0.000488859,0.0156783,0.0002255205,0.00003471868,0.000003028395,0.002768579,0.04831654,0.1217076,0.8047684,0.004770796,0.0002428983],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6674408,0.0001613238,0.3053354,0.01622593,0.001238609,0.004116622,0.00002894418,0.0001130461,0.005339356],"genre_scores_gemma":[0.9677308,0.000009590512,0.03142178,0.0004800568,0.00006276392,0.00009428709,4.545223e-7,0.000005713973,0.0001945318],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9380126,"threshold_uncertainty_score":0.3467439,"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."}}