{"id":"W2513414733","doi":"10.1109/sai.2016.7556026","title":"A density-based data cleaning approach for deduplication with data consistency and accuracy","year":2016,"lang":"en","type":"article","venue":"2016 SAI Computing Conference (SAI)","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University","funders":"","keywords":"Data deduplication; Computer science; Data mining; Correctness; Data warehouse; Data quality; Tuple; Data transformation; Consistency (knowledge bases); Scalability; Data consistency; Data modeling; Data set; Database; Data integrity; Set (abstract data type); Algorithm; Artificial intelligence; Mathematics","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":[0.005960433,0.0002351657,0.0003900812,0.0001615827,0.0004224492,0.0007973299,0.003572036,0.00007366818,0.00003745212],"category_scores_gemma":[0.005022718,0.0001411539,0.00002763475,0.0002874612,0.0003282972,0.001227319,0.002670178,0.000105327,0.00007314172],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002700786,"about_ca_system_score_gemma":0.0003694673,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001205973,"about_ca_topic_score_gemma":0.00008011714,"domain_scores_codex":[0.996304,0.0002699591,0.0006547307,0.001625794,0.0007412083,0.0004042967],"domain_scores_gemma":[0.9903907,0.00386167,0.0005871859,0.004487969,0.0005115604,0.0001608689],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001546884,0.0001567576,0.004656238,0.00008053494,0.00006318272,0.000002874186,0.0002013646,0.00002511128,0.0003346727,0.04588323,0.0456972,0.9027441],"study_design_scores_gemma":[0.003913671,0.0002856824,0.014247,0.0006521974,0.0001903802,0.00002505865,0.001704682,0.7024488,0.0002643889,0.01036221,0.2648785,0.001027402],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01451239,0.00005192398,0.9797456,0.002861469,0.00008974913,0.0006836994,0.0004597144,0.000102925,0.001492521],"genre_scores_gemma":[0.8668959,0.00001814706,0.1311161,0.0008169618,0.0001059993,0.000009748591,0.0007391997,0.00001693888,0.0002809842],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9017168,"threshold_uncertainty_score":0.7688671,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4115022651312117,"score_gpt":0.4283854050917017,"score_spread":0.01688313996049001,"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."}}