{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005795221,0.00004860729,0.00007745829,0.00004560251,0.0001191036,0.00005777362,0.001626816,0.0000169955,0.000001216785],"category_scores_gemma":[0.0004242747,0.00002743142,0.00002284262,0.00008039321,0.00002159361,0.005095755,0.000725029,0.00007107257,0.000002422553],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001546833,"about_ca_system_score_gemma":0.0000520093,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":9.744011e-7,"about_ca_topic_score_gemma":0.000001687261,"domain_scores_codex":[0.9994003,0.00001605081,0.0002517604,0.0000632058,0.0001810676,0.00008764749],"domain_scores_gemma":[0.9985266,0.00005979834,0.0001997902,0.001058831,0.00009106402,0.00006394755],"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":[0.00004652206,0.00004186936,0.0004332519,0.00002850688,0.00002066758,2.287398e-7,0.001755253,0.00666752,0.00009495239,0.9414344,0.0110544,0.03842248],"study_design_scores_gemma":[0.00102357,0.000241655,0.006798297,0.00006467461,0.0000198451,0.0006249865,0.00035596,0.1768706,0.0003766293,0.02875652,0.7846454,0.0002218271],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01029592,0.00003979861,0.9856798,0.003370895,0.0001295734,0.0001122745,0.00004010795,0.000005670766,0.0003259453],"genre_scores_gemma":[0.1334751,0.000004381615,0.8657036,0.0005710383,0.0001986022,0.000002350695,0.00001043678,0.000002450359,0.00003198127],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9126778,"threshold_uncertainty_score":0.3694299,"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."}}