{"id":"W2140609014","doi":"10.1145/1007568.1007650","title":"Information-theoretic tools for mining database structure from large data sets","year":2004,"lang":"en","type":"article","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":55,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Data mining; Redundancy (engineering); Categorical variable; Ranking (information retrieval); Data redundancy; Data modeling; Set (abstract data type); Information retrieval; Database; Machine learning","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":["scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.002373721,0.0001087006,0.000165188,0.000110177,0.0001700636,0.001142005,0.00210773,0.00004376587,0.002035787],"category_scores_gemma":[0.006131345,0.00007599367,0.00003180579,0.0002469731,0.000044391,0.007230584,0.001313209,0.00005734218,0.0004455198],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001729538,"about_ca_system_score_gemma":0.00006443176,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001007352,"about_ca_topic_score_gemma":0.000436577,"domain_scores_codex":[0.9980547,0.00005012377,0.0005562114,0.0003182675,0.0007876337,0.0002331067],"domain_scores_gemma":[0.9965046,0.0009584162,0.0001662381,0.002182412,0.0001031901,0.00008516572],"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":[0.00003857578,0.00004880699,0.00008124265,0.00002042384,0.00003882945,0.000002244755,0.002027397,0.0001888939,0.00002549569,0.5513182,0.3340656,0.1121442],"study_design_scores_gemma":[0.001310478,0.00002401872,0.0006385615,0.0000174984,0.00002470283,9.173102e-7,0.0103566,0.003464849,0.0001928241,0.2146045,0.7691741,0.0001909084],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05800418,0.00002811456,0.8676493,0.00304785,0.0005564376,0.0005469297,0.06534448,0.00007341007,0.004749333],"genre_scores_gemma":[0.7836753,0.00001103499,0.1638467,0.009574618,0.0001171508,0.00001543799,0.0423777,0.000009415262,0.0003726647],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7256711,"threshold_uncertainty_score":0.9998949,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2199736201345843,"score_gpt":0.4288470871589206,"score_spread":0.2088734670243363,"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."}}