{"id":"W2962752375","doi":"10.4230/lipics.icdt.2019.6","title":"A Formal Framework for Probabilistic Unclean Databases.","year":2019,"lang":"en","type":"article","venue":"DROPS (Schloss Dagstuhl – Leibniz Center for Informatics)","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":22,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Probabilistic logic; Computer science; Tuple; Cardinality (data modeling); Database; Probabilistic database; Realization (probability); Data mining; Theoretical computer science; Database theory; Database design; Artificial intelligence; Mathematics","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":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.005921926,0.000482094,0.0008206205,0.0004441057,0.0004737867,0.001013035,0.002351449,0.0002161173,0.0005734117],"category_scores_gemma":[0.004048212,0.0003762308,0.0004944293,0.0006364348,0.0001836601,0.004297352,0.001237981,0.0004202593,0.002270153],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001348873,"about_ca_system_score_gemma":0.0001233095,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001862774,"about_ca_topic_score_gemma":0.00005217171,"domain_scores_codex":[0.9938823,0.00008126233,0.002459985,0.0006230607,0.001710445,0.001242948],"domain_scores_gemma":[0.9934753,0.002230088,0.0009820468,0.002380971,0.0006168958,0.0003147145],"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":[0.0008097622,0.0006647854,0.005816285,0.001505673,0.0002473922,0.000002523675,0.006357152,0.0003040439,0.000007046581,0.8122048,0.08001695,0.09206363],"study_design_scores_gemma":[0.003096557,0.0004716088,0.0008885271,0.0002100336,0.0000737871,0.00001140817,0.005856572,0.02773209,0.00007626743,0.06983855,0.891052,0.0006925866],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1134554,0.00002678994,0.8554391,0.001457039,0.003201579,0.006668034,0.009539324,0.0002495473,0.009963198],"genre_scores_gemma":[0.8148492,0.00002818829,0.1608752,0.01065794,0.0005773781,0.0009677893,0.00558068,0.0001341069,0.006329525],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8110351,"threshold_uncertainty_score":0.999869,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1331143116709655,"score_gpt":0.405443553735199,"score_spread":0.2723292420642335,"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."}}