{"id":"W2066070009","doi":"10.1109/bigdata.congress.2014.53","title":"Reducing the Search Space for Big Data Mining for Interesting Patterns from Uncertain Data","year":2014,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":67,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Manitoba","funders":"","keywords":"Computer science; Big data; Uncertain data; Data mining; Database transaction; Transaction data; Data stream mining; Probabilistic logic; Space (punctuation); Data science; Database; Artificial intelligence","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":["open_science"],"consensus_categories":[],"category_scores_codex":[0.001542297,0.0001083143,0.000118959,0.00003292858,0.000356728,0.0005290019,0.00657079,0.00002912044,0.00000334288],"category_scores_gemma":[0.0006138979,0.00007576597,0.00001944847,0.0001334752,0.00003111252,0.0005171099,0.003727189,0.00008459516,0.000006350093],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001201668,"about_ca_system_score_gemma":0.00006571897,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001695793,"about_ca_topic_score_gemma":0.0002772386,"domain_scores_codex":[0.9984445,0.00004392002,0.0002069565,0.000859006,0.0001465393,0.0002990828],"domain_scores_gemma":[0.9931252,0.002140257,0.00007664369,0.004532464,0.00006257057,0.00006284164],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000002036609,0.00001849467,0.0001271634,0.0000134551,0.00001818525,1.508389e-7,0.0005029285,0.00004526028,0.0002204297,0.004941035,0.0351653,0.9589456],"study_design_scores_gemma":[0.0001766011,0.00002807599,0.0001843875,0.00005370073,0.00001044964,0.000001581389,0.000371733,0.944854,0.0003043078,0.0006400919,0.05326162,0.0001134337],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.004027999,0.00001717938,0.9864359,0.006927095,0.0004027922,0.0003300407,0.001579681,0.00009314391,0.000186162],"genre_scores_gemma":[0.08988326,0.000002764858,0.905921,0.0003816197,0.001073581,0.00006619227,0.002335032,0.00001652124,0.000319972],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9588321,"threshold_uncertainty_score":0.9988042,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3019733450573061,"score_gpt":0.374375308833241,"score_spread":0.07240196377593494,"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."}}