{"id":"W2748020237","doi":"10.1007/978-3-319-56994-9_78","title":"Corroborating Quality of Data Through Density Information","year":2017,"lang":"en","type":"book-chapter","venue":"Lecture notes in networks and systems","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":false,"ca_institutions":"McMaster University","funders":"","keywords":"Data deduplication; Tuple; Data quality; Computer science; Master data; Data mining; Data integration; Process (computing); Quality (philosophy); Data integrity; Data pre-processing; Database; Data science; Engineering","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":[0.008421315,0.0005980736,0.000912585,0.004020251,0.0006592843,0.004023487,0.002150162,0.001927189,0.003303816],"category_scores_gemma":[0.07757957,0.0006483038,0.0006668424,0.004368098,0.004568234,0.006591124,0.00325529,0.001953647,0.0008843506],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001268337,"about_ca_system_score_gemma":0.0007468858,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001508151,"about_ca_topic_score_gemma":0.001529788,"domain_scores_codex":[0.99098,0.003389385,0.0004224726,0.001169259,0.003756834,0.000282186],"domain_scores_gemma":[0.9200827,0.05853935,0.004924256,0.01049602,0.0054631,0.0004945152],"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":[0.0006240273,0.0001757015,0.07094774,0.001037433,0.000439734,0.000360556,0.001623263,0.05316442,0.01940237,0.4042388,0.01085542,0.4371306],"study_design_scores_gemma":[0.00007582254,0.0002800565,0.03251082,0.0004666142,0.0002472732,0.0008030027,0.001198783,0.2630741,0.04055482,0.6347156,0.02586582,0.0002072866],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1256784,0.003776757,0.8119822,0.005880786,0.0007075789,0.000143721,0.002152706,0.0008311472,0.04884662],"genre_scores_gemma":[0.8397116,0.002204537,0.1525508,0.0004712347,0.0006186884,0.00009188547,0.001312694,0.000154163,0.002884367],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008421315,"threshold_uncertainty_score":0.04453671,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3017625718409327,"score_gpt":0.4222852155345378,"score_spread":0.120522643693605,"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."}}