{"id":"W2008641248","doi":"10.1109/icde.2010.5447744","title":"ProbClean: A probabilistic duplicate detection system","year":2010,"lang":"en","type":"article","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Probabilistic logic; Data mining; Set (abstract data type); Space (punctuation); Relational database; Quality (philosophy); Artificial intelligence","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.003480023,0.00007735794,0.0001266535,0.000113578,0.0001289695,0.0003347457,0.0006113428,0.00004631537,0.0004153237],"category_scores_gemma":[0.001214011,0.0000500302,0.00005080325,0.0004038777,0.00006207287,0.0002814915,0.0001976281,0.0001233745,0.003730958],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001826132,"about_ca_system_score_gemma":0.00001496402,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008791895,"about_ca_topic_score_gemma":0.001043954,"domain_scores_codex":[0.9982737,0.00008247811,0.0003953505,0.0004056909,0.0006800492,0.0001627633],"domain_scores_gemma":[0.9985832,0.0001962747,0.0001107574,0.0008894062,0.0001370471,0.00008333563],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00002879941,0.0001125576,0.0001928232,0.00006053355,0.00001347745,0.000005591624,0.000195773,0.00003490825,0.01270715,0.7522672,0.01251499,0.2218662],"study_design_scores_gemma":[0.0006028905,0.0001581756,0.01008004,0.00001787881,0.00003403493,0.00004669331,0.002973134,0.03889312,0.01012298,0.08181336,0.8547871,0.0004706466],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.3951392,0.000006061144,0.3250794,0.002569728,0.002821977,0.001654431,0.0000221602,0.0008303019,0.2718768],"genre_scores_gemma":[0.9909145,2.008342e-7,0.001832712,0.0001537411,0.00007475197,0.00005383787,0.000001760538,0.000004880004,0.006963645],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.842272,"threshold_uncertainty_score":0.9970447,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1025191169551138,"score_gpt":0.372236251015045,"score_spread":0.2697171340599311,"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."}}