{"id":"W2113415503","doi":"10.14778/1687627.1687695","title":"Modeling and querying possible repairs 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":57,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Scalability; Data mining; Parameterized complexity; Cluster analysis; Identification (biology); Set (abstract data type); Database; Algorithm; Machine learning","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":[0.01872432,0.001144262,0.002760555,0.004097712,0.001648826,0.006319058,0.006495992,0.003068219,0.001216079],"category_scores_gemma":[0.09447894,0.001862285,0.003144493,0.006874503,0.00319885,0.0115789,0.004885925,0.002656908,0.0002922386],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003210404,"about_ca_system_score_gemma":0.002540408,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007569163,"about_ca_topic_score_gemma":0.005265913,"domain_scores_codex":[0.9776638,0.008640594,0.002352148,0.004332245,0.005863267,0.001147972],"domain_scores_gemma":[0.9190702,0.05695133,0.006902297,0.0127965,0.003520522,0.0007592313],"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":[0.0002914258,0.0001244959,0.007417529,0.000256908,0.0001693509,0.0003464878,0.0008726926,0.8803123,0.001532735,0.05922704,0.001131288,0.04831785],"study_design_scores_gemma":[0.000024901,0.00006799228,0.0004971216,0.0000379837,0.00004871634,0.0002702402,0.0002839845,0.9009045,0.002220256,0.09434089,0.001264216,0.00003914677],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06035079,0.0006497884,0.936168,0.00066856,0.00001907204,0.0001182721,0.0007298392,0.000555653,0.00074003],"genre_scores_gemma":[0.5881552,0.0006878045,0.4079065,0.0001967362,0.00006462571,0.0003247919,0.001745372,0.00012815,0.0007908278],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01872432,"threshold_uncertainty_score":0.09902489,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08693929288766766,"score_gpt":0.3472986307308046,"score_spread":0.260359337843137,"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."}}