{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002727829,0.00006620826,0.0001043903,0.0001463892,0.0001961011,0.00005238981,0.001244082,0.00005182555,0.000003492007],"category_scores_gemma":[0.001079303,0.00004136072,0.00003037111,0.0009193638,0.0001021629,0.001252261,0.0004179901,0.00008094985,0.000002757348],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007219699,"about_ca_system_score_gemma":0.00003092895,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006138262,"about_ca_topic_score_gemma":1.730413e-7,"domain_scores_codex":[0.9983703,0.000006108231,0.0003152454,0.0002786551,0.0008296573,0.0001999799],"domain_scores_gemma":[0.9989746,0.0003522057,0.0004990104,0.00001593814,0.000132584,0.00002564876],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.000004851933,0.0002196126,0.1654428,0.00006370863,0.00002364333,2.305198e-8,0.001072231,0.00005697251,0.4778263,0.2740455,0.004797349,0.07644708],"study_design_scores_gemma":[0.0008760278,0.00005414042,0.6179377,0.0007277145,0.00001269851,0.00001538312,0.000237664,0.07291115,0.1508969,0.1513814,0.004544479,0.0004047018],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9661162,0.00009366687,0.008952887,0.01993277,0.00007938022,0.0003258807,0.000437286,0.00007199875,0.00398994],"genre_scores_gemma":[0.9306648,0.000008265668,0.06903344,0.0001754022,0.00004518042,0.00001042616,5.699464e-7,0.000002148892,0.00005972809],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4524949,"threshold_uncertainty_score":0.2311835,"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."}}