{"id":"W2530130430","doi":"","title":"Data quality through active constraint discovery and maintenance","year":2012,"lang":"en","type":"dissertation","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Leverage (statistics); Constraint (computer-aided design); Data integrity; Data quality; Data mining; Relation (database); Quality (philosophy); Set (abstract data type); Domain (mathematical analysis); Machine learning; Engineering; Mathematics; Database","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":[0.005149002,0.0002688997,0.0005494527,0.00008886006,0.0001490063,0.000742082,0.001957502,0.000173473,0.001101632],"category_scores_gemma":[0.003326615,0.0001812437,0.00007207514,0.0002300124,0.0002159131,0.004002779,0.0008881636,0.0002634735,0.000324936],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000329573,"about_ca_system_score_gemma":0.0001127886,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001055467,"about_ca_topic_score_gemma":0.008204427,"domain_scores_codex":[0.9959001,0.0003620119,0.0008993699,0.001131598,0.001366562,0.0003403679],"domain_scores_gemma":[0.9952402,0.001304404,0.0006401779,0.002551277,0.0001672588,0.0000966416],"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":[0.000198224,0.0001482161,0.0001485851,0.0001043207,0.0001383883,0.000005013657,0.002334108,2.597372e-7,0.00005268523,0.5801761,0.2059359,0.2107582],"study_design_scores_gemma":[0.0003994115,0.00002642848,0.07073952,0.00008735451,0.00009386389,0.000002981313,0.08929137,0.00001911587,0.0001498354,0.1173496,0.7212433,0.0005972466],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.04458545,0.0008627187,0.04586496,0.00283488,0.004438496,0.001263195,0.01877011,0.0001210486,0.8812591],"genre_scores_gemma":[0.5507504,0.0006827387,0.004276696,0.00219133,0.0003630344,0.00004213537,0.02482215,0.00004046309,0.416831],"genre_candidate":"other","genre_consensus":null,"teacher_disagreement_score":0.5153074,"threshold_uncertainty_score":0.9998115,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4121116768603989,"score_gpt":0.5156160078328202,"score_spread":0.1035043309724213,"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."}}