{"id":"W2158763191","doi":"10.1145/1059513.1059519","title":"An information-theoretic approach to normal forms for relational and XML data","year":2005,"lang":"en","type":"article","venue":"Journal of the ACM","topic":"Advanced Database Systems and Queries","field":"Computer Science","cited_by":100,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Relational database; Normalization (sociology); XML; Relational model; Database normalization; Information retrieval; Data mining; Measure (data warehouse); Theoretical computer science; Set (abstract data type); Programming language; Artificial intelligence; Cluster analysis","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":[0.02870125,0.001430822,0.001683536,0.006453341,0.002266741,0.01078014,0.00417277,0.003502863,0.005060656],"category_scores_gemma":[0.08525213,0.001340145,0.003028712,0.009620923,0.01887443,0.02657544,0.005448991,0.00829809,0.001744666],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.005306572,"about_ca_system_score_gemma":0.002925521,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001448006,"about_ca_topic_score_gemma":0.001026479,"domain_scores_codex":[0.957243,0.01740416,0.005860485,0.00521352,0.01330019,0.0009787322],"domain_scores_gemma":[0.9400191,0.0342496,0.003868127,0.01348422,0.007563915,0.0008150239],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00001356354,0.00001493412,0.0001473941,0.00005219704,0.000008794408,0.000033458,0.0002318438,0.002157353,0.0002916906,0.9840077,0.0007571616,0.01228406],"study_design_scores_gemma":[0.000008162981,0.00002309376,0.00005262273,0.0000412044,0.000007091741,0.0001044569,0.00006213294,0.01048081,0.0007831471,0.9794612,0.008956778,0.00001933056],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003004533,0.000529638,0.9891867,0.001566936,0.0001500439,0.0001321019,0.00017656,0.0002184852,0.005034947],"genre_scores_gemma":[0.09155771,0.00115669,0.8997121,0.0009830679,0.0008205055,0.0009064594,0.0005006398,0.0002863459,0.004076398],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.02870125,"threshold_uncertainty_score":0.1517885,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0304874038357801,"score_gpt":0.2772800273680918,"score_spread":0.2467926235323117,"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."}}