{"id":"W2139422684","doi":"10.1145/335191.336572","title":"Towards data mining benchmarking","year":2000,"lang":"en","type":"article","venue":"ACM SIGMOD Record","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science; Data mining; Benchmarking; Data stream mining; Database transaction; Association rule learning; Apriori algorithm; Set (abstract data type); GSP Algorithm; Database; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.08084901,0.002452552,0.003663776,0.006299605,0.002101195,0.01771752,0.008426043,0.004187661,0.006156892],"category_scores_gemma":[0.193538,0.001373507,0.002282878,0.01131553,0.003610177,0.02364633,0.01280698,0.01035358,0.006223383],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.004715338,"about_ca_system_score_gemma":0.007458016,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001529866,"about_ca_topic_score_gemma":0.0008749549,"domain_scores_codex":[0.9033338,0.04877502,0.008951464,0.009044292,0.02728341,0.002611972],"domain_scores_gemma":[0.8826397,0.03821084,0.003899374,0.04006594,0.03171855,0.003465533],"domain_codex":null,"domain_gemma":"evaluation","domain_candidate":"evaluation","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.000494394,0.0009710113,0.009077013,0.001994987,0.0003386948,0.0002388005,0.001000243,0.04510951,0.004129776,0.3878365,0.08371024,0.4650989],"study_design_scores_gemma":[0.0001690634,0.0007037732,0.002613924,0.001719209,0.0001134227,0.0004603865,0.00141129,0.2265739,0.01178222,0.4658794,0.2884075,0.0001658254],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0127103,0.008093272,0.904648,0.02819348,0.002666995,0.001412024,0.002398866,0.009161321,0.03071571],"genre_scores_gemma":[0.1305668,0.006076145,0.8335759,0.007293133,0.001326886,0.002414981,0.01113701,0.002237383,0.005371714],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.919151,"threshold_uncertainty_score":0.4275755,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05942132737752803,"score_gpt":0.2999806763587709,"score_spread":0.2405593489812429,"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."}}