{"id":"W2021255304","doi":"10.1007/s00778-013-0316-z","title":"Sampling from repairs of conditional functional dependency violations","year":2013,"lang":"en","type":"article","venue":"The VLDB Journal","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":46,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Dependency (UML); Functional dependency; Data mining; Sampling (signal processing); Class (philosophy); Space (punctuation); Variety (cybernetics); Semantics (computer science); Artificial intelligence; Relational database; 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":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.002777442,0.00006720267,0.0001266322,0.0001303604,0.0004084485,0.000276813,0.0006001603,0.00002875357,0.0199871],"category_scores_gemma":[0.001168218,0.00003846421,0.0001227976,0.0002307146,0.0001049777,0.0006429749,0.0001409741,0.0002034185,0.0010578],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002168323,"about_ca_system_score_gemma":0.00006853491,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001395372,"about_ca_topic_score_gemma":0.00003004597,"domain_scores_codex":[0.9976121,0.0002375127,0.0006314425,0.0001489158,0.001239883,0.0001301435],"domain_scores_gemma":[0.9973035,0.001510576,0.0003833292,0.0003579644,0.0003674103,0.00007721853],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001034241,0.0003871441,0.02795779,0.000005219534,0.0004660455,0.00000876316,0.001960618,0.01050198,0.005718399,0.1986555,0.6547427,0.09949247],"study_design_scores_gemma":[0.0001917089,0.00001850101,0.2417914,0.000009104972,0.00001747089,0.00002413864,0.001465426,0.001197145,0.00005459741,0.7391202,0.01605517,0.0000551596],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5255728,0.0001487563,0.4582621,0.008137734,0.001128142,0.000184481,0.0002022357,0.00002368583,0.006340053],"genre_scores_gemma":[0.9938018,0.00001790979,0.004236419,0.0005221294,0.0003556575,0.000005609836,0.00003473131,0.000004032951,0.001021724],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6386875,"threshold_uncertainty_score":0.99972,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3025801455678561,"score_gpt":0.4077661213846789,"score_spread":0.1051859758168228,"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."}}