{"id":"W833149042","doi":"","title":"Deriving Effectiveness Measures for Data Quality Rules","year":2014,"lang":"en","type":"article","venue":"","topic":"Hermeneutics and Narrative Identity","field":"Arts and Humanities","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Data mining; Data quality; Python (programming language); Bayesian network; Quality (philosophy); Artificial intelligence; Programming language","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":[0.03039515,0.001710841,0.001747355,0.01747336,0.001513719,0.00654688,0.002655306,0.002108101,0.0032884],"category_scores_gemma":[0.2429316,0.0009768091,0.002584418,0.006055349,0.003452818,0.009412652,0.003698965,0.002692946,0.0006893835],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.004490793,"about_ca_system_score_gemma":0.003378939,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003124477,"about_ca_topic_score_gemma":0.003146701,"domain_scores_codex":[0.9456818,0.01913961,0.007421707,0.004088623,0.02211003,0.001558163],"domain_scores_gemma":[0.7505161,0.2010351,0.01474855,0.01382257,0.01867837,0.001199283],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0002680073,0.0003338606,0.03387902,0.00193466,0.0005816542,0.0004939268,0.001458438,0.211206,0.004560693,0.2876863,0.004423165,0.4531743],"study_design_scores_gemma":[0.00008003191,0.0002377397,0.007112004,0.0007816415,0.0003214267,0.000450807,0.0008946166,0.6290128,0.01347586,0.3399481,0.007565849,0.0001191378],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03283121,0.0006722918,0.9570507,0.0007091694,0.00005051572,0.0005926364,0.001195058,0.001160426,0.005738006],"genre_scores_gemma":[0.2926017,0.0004732127,0.7034191,0.000194916,0.00008513683,0.000859765,0.001684998,0.0002883995,0.0003928528],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.03039515,"threshold_uncertainty_score":0.1607468,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1756505818528511,"score_gpt":0.3463726701828384,"score_spread":0.1707220883299873,"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."}}