{"id":"W2128322880","doi":"10.4018/jdwm.2005040101","title":"The Use of Smart Tokens in Cleaning Integrated Warehouse Data","year":2005,"lang":"en","type":"article","venue":"International Journal of Data Warehousing and Mining","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":24,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Windsor","funders":"","keywords":"Computer science; Data warehouse; Security token; Database; Alphanumeric; Matching (statistics); Data mining; Unique identifier; Identifier; Computer security","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":[0.006902506,0.0001022445,0.0002314158,0.0003615098,0.0001041627,0.0007253884,0.003884193,0.00003392077,0.00002448602],"category_scores_gemma":[0.007062009,0.0000656079,0.00003136472,0.0002528907,0.0001286558,0.003771463,0.002357791,0.0002156128,0.000004682942],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004203997,"about_ca_system_score_gemma":0.0001113902,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002050584,"about_ca_topic_score_gemma":0.001558771,"domain_scores_codex":[0.9968622,0.0002321134,0.001244105,0.0002994127,0.001202144,0.0001599745],"domain_scores_gemma":[0.9953704,0.002258016,0.0008217167,0.001037953,0.0004496118,0.00006234185],"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":[0.0001813343,0.0000729918,0.004116633,0.000002300421,0.00009823968,0.00004714804,0.00117751,0.001358081,0.00005221083,0.0002370691,0.04211592,0.9505405],"study_design_scores_gemma":[0.0006335841,0.00005359472,0.002256615,0.0002716028,0.00002567111,0.00009836535,0.004651642,0.0492305,0.00004852615,0.0001897039,0.9424344,0.0001058474],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9222223,0.001280303,0.05856626,0.01349324,0.002221673,0.0001600704,0.001739164,0.00002557717,0.0002914741],"genre_scores_gemma":[0.9577079,0.000624631,0.04055461,0.0005263026,0.0002541089,2.892073e-7,0.0001372881,0.00001213522,0.0001827319],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9504347,"threshold_uncertainty_score":0.8454394,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.5821457750325668,"score_gpt":0.474360714999418,"score_spread":0.1077850600331489,"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."}}