{"id":"W1995541812","doi":"10.1007/s00778-009-0161-2","title":"Creating probabilistic databases from duplicated data","year":2009,"lang":"en","type":"article","venue":"The VLDB Journal","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":61,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Probabilistic logic; Data mining; Scalability; Data deduplication; Task (project management); Cluster analysis; Database; String (physics); Probabilistic database; Information retrieval; Machine learning; Artificial intelligence; Database theory; Relational database","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":[],"category_scores_codex":[0.0078893,0.0001047428,0.0001836691,0.00008003911,0.0005475497,0.0008991892,0.003927862,0.00001728822,0.001195681],"category_scores_gemma":[0.007211903,0.00005363205,0.00004274647,0.0004019612,0.00008975453,0.0009507232,0.0007711769,0.0002714593,0.0005578696],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002006482,"about_ca_system_score_gemma":0.00005834699,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001481652,"about_ca_topic_score_gemma":0.00006520312,"domain_scores_codex":[0.9972023,0.000427707,0.000631218,0.0003695762,0.001136882,0.0002323122],"domain_scores_gemma":[0.9954342,0.001539673,0.0003613883,0.002431924,0.0001172501,0.0001156101],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0000921679,0.0002396536,0.0005343524,0.000001941033,0.00006524661,0.00005883014,0.0007895941,0.000358862,0.0006994362,0.0189341,0.5360802,0.4421456],"study_design_scores_gemma":[0.000629178,0.00009594285,0.03953699,0.00007246639,0.0001140399,0.0001060638,0.002344685,0.01327663,0.000120373,0.3403775,0.6030555,0.0002706689],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5293232,0.002423555,0.2997091,0.1126383,0.002300991,0.00120784,0.003881123,0.000291307,0.04822454],"genre_scores_gemma":[0.9837586,0.0001351775,0.008627635,0.004425716,0.0009578771,0.000002062397,0.0003376612,0.00001003771,0.001745218],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4544354,"threshold_uncertainty_score":0.9997174,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4798807441543463,"score_gpt":0.4770797275385156,"score_spread":0.002801016615830709,"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."}}