{"id":"W2341381658","doi":"10.1073/pnas.1604553113","title":"Boosting association rule mining in large datasets via Gibbs sampling","year":2016,"lang":"en","type":"article","venue":"Proceedings of the National Academy of Sciences","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"Department of Health and Aged Care, Australian Government; National Health and Medical Research Council; Natural Sciences and Engineering Research Council of Canada; Government of Canada","keywords":"Association rule learning; Data mining; Computer science; Boosting (machine learning); Markov chain; Apriori algorithm; Database transaction; A priori and a posteriori; Machine learning","routes":{"ca_aff":true,"ca_fund":true,"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":[0.01169734,0.000893458,0.002817535,0.002007873,0.0009473162,0.001389969,0.002332255,0.001178962,0.001149875],"category_scores_gemma":[0.02476886,0.00104252,0.001688931,0.002335913,0.00158068,0.002537032,0.002378484,0.002287972,0.0005974316],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006771846,"about_ca_system_score_gemma":0.001592567,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002034238,"about_ca_topic_score_gemma":0.00358424,"domain_scores_codex":[0.9960209,0.002177245,0.0002125361,0.0005579081,0.0008637549,0.0001676708],"domain_scores_gemma":[0.9773526,0.01859822,0.000576044,0.00178257,0.001393142,0.000297579],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003587283,0.0003994024,0.01040042,0.0002618502,0.0003689607,0.0002704202,0.0003015304,0.7482828,0.004872051,0.04168116,0.002492137,0.1903104],"study_design_scores_gemma":[0.00002621009,0.00003795803,0.0002886173,0.00000699986,0.00001979255,0.0000352811,0.00000962614,0.9835834,0.0005787447,0.01510014,0.0003061543,0.000007026373],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03703285,0.0002878845,0.9610627,0.0002660126,0.00002904673,0.00009868087,0.00006030561,0.0006131377,0.000549395],"genre_scores_gemma":[0.4087147,0.0004092274,0.5883242,0.0004244769,0.0001467746,0.000465095,0.0006091997,0.0001259495,0.000780367],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01169734,"threshold_uncertainty_score":0.06186217,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04792729368646059,"score_gpt":0.3224678562511851,"score_spread":0.2745405625647245,"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."}}