{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003869678,0.0000917127,0.0001726247,0.00009248174,0.00006401042,0.0001564212,0.001688209,0.00002427823,0.00008126148],"category_scores_gemma":[0.001958987,0.00004972197,0.00009150177,0.0004905285,0.00009906138,0.0003781865,0.001001373,0.00007029202,0.0002545429],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004662251,"about_ca_system_score_gemma":0.00002751585,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006843983,"about_ca_topic_score_gemma":0.000004451392,"domain_scores_codex":[0.9973964,0.00001497049,0.000444936,0.0002710035,0.001691676,0.0001810126],"domain_scores_gemma":[0.9988549,0.0000811193,0.000303299,0.00027498,0.0003811485,0.0001045063],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00005158316,0.0001694627,0.005958328,0.00002003826,0.00003560149,3.903135e-7,0.001941339,0.00002384897,0.001426798,0.2306601,0.7403725,0.01933998],"study_design_scores_gemma":[0.0006382784,0.00009866243,0.003102693,0.00002797255,0.00002604106,0.000003994799,0.0062122,0.0001278697,0.03136922,0.2495157,0.7087362,0.0001411328],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.4788121,0.000271956,0.0004179185,0.02637879,0.001933811,0.001111165,0.00005469319,0.0001015104,0.4909181],"genre_scores_gemma":[0.9904682,0.000007201678,0.00106456,0.0007065865,0.00006562925,0.00001941607,7.501254e-7,0.000005446402,0.007662233],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5116561,"threshold_uncertainty_score":0.3271719,"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."}}