{"id":"W2262592273","doi":"10.14778/2824032.2824109","title":"KATARA","year":2015,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":45,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Table (database); Crowdsourcing; Ambiguity; Tuple; Information retrieval; Annotation; Task (project management); Semantics (computer science); Reliability (semiconductor); Data mining; World Wide Web; Programming language; Artificial intelligence","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":[0.003584919,0.001385533,0.001360952,0.003349873,0.002107025,0.006382401,0.00282138,0.002075268,0.1934733],"category_scores_gemma":[0.01186902,0.001070332,0.001377244,0.002788434,0.0009913269,0.006307074,0.007136745,0.002439921,0.2077992],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0013824,"about_ca_system_score_gemma":0.003356838,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002117492,"about_ca_topic_score_gemma":0.002176022,"domain_scores_codex":[0.9956524,0.0006680354,0.0004413979,0.001461322,0.001385047,0.0003917463],"domain_scores_gemma":[0.9912677,0.001256124,0.0005382373,0.00333904,0.002718168,0.0008806323],"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":[0.001154034,0.0001914484,0.007184934,0.001874542,0.0001984742,0.0007565383,0.001112701,0.002005992,0.01260154,0.04359755,0.4071482,0.5221741],"study_design_scores_gemma":[0.00005280194,0.00007480574,0.001735892,0.0002578816,0.00005833311,0.0006711484,0.0002841507,0.003208101,0.00663353,0.01469011,0.972272,0.00006125144],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.02286632,0.007839766,0.3081153,0.01293324,0.008711325,0.001232062,0.05623797,0.1179418,0.4641222],"genre_scores_gemma":[0.1411803,0.005686155,0.2611118,0.006753407,0.001957954,0.001488411,0.1163295,0.02005184,0.4454404],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.1934733,"threshold_uncertainty_score":0,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3440476576255437,"score_gpt":0.4117242000185209,"score_spread":0.06767654239297716,"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."}}