{"id":"W2214080290","doi":"10.1145/2700409","title":"Classification with Streaming Features: An Emerging-Pattern Mining Approach","year":2015,"lang":"en","type":"article","venue":"ACM Transactions on Knowledge Discovery from Data","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":33,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science; Streaming data; Feature selection; Data mining; Benchmark (surveying); Classifier (UML); Curse of dimensionality; Feature (linguistics); Machine learning; Artificial intelligence; Feature vector; Pattern recognition (psychology)","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":[],"consensus_categories":[],"category_scores_codex":[0.0002823343,0.0002583999,0.000204905,0.0001506265,0.000305398,0.0006896158,0.00408963,0.00008465454,0.000006092324],"category_scores_gemma":[0.00003102262,0.0002229078,0.00003379272,0.0006023531,0.00007497743,0.004448361,0.0001492353,0.0002624347,0.00005466597],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007163878,"about_ca_system_score_gemma":0.0002262979,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004466119,"about_ca_topic_score_gemma":0.0005469379,"domain_scores_codex":[0.997856,0.00008783719,0.0002636352,0.001176781,0.0003220275,0.0002937622],"domain_scores_gemma":[0.9941777,0.0001458333,0.0001142054,0.005239149,0.00009999767,0.0002231195],"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":[0.00002530569,0.001397221,0.000352817,0.00001382769,0.0001150014,0.00000449387,0.004822991,0.000445183,0.0001374331,0.0006365609,0.003538706,0.9885104],"study_design_scores_gemma":[0.002300377,0.0005671641,0.01248366,0.000233874,0.0002511609,0.00005479934,0.01166748,0.9490593,0.000846795,0.0009757802,0.02008865,0.001470974],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01198396,0.0001176583,0.9838828,0.0004278727,0.0002481344,0.0001946484,0.002129228,0.0002348712,0.0007808366],"genre_scores_gemma":[0.6339324,0.00002204554,0.3589927,0.00008992276,0.0001823147,0.0001092064,0.00618889,0.00003852311,0.0004439837],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9870395,"threshold_uncertainty_score":0.9089915,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1110131822858443,"score_gpt":0.3239055552908267,"score_spread":0.2128923730049824,"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."}}