{"id":"W2140677665","doi":"10.1080/713827182","title":"Web-log cleaning for constructing sequential classifiers","year":2003,"lang":"en","type":"article","venue":"Applied Artificial Intelligence","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science; Association rule learning; Data mining; Feature selection; Machine learning; Web server; Construct (python library); Information retrieval; Artificial intelligence; World Wide Web; The Internet","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":[],"consensus_categories":[],"category_scores_codex":[0.002896815,0.001156469,0.001796053,0.002969106,0.001120211,0.001157691,0.001822454,0.001300954,0.002668793],"category_scores_gemma":[0.01492979,0.000891938,0.001339251,0.002067985,0.0004115606,0.002746193,0.001122658,0.001715888,0.002179004],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007734487,"about_ca_system_score_gemma":0.002652971,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00632715,"about_ca_topic_score_gemma":0.007100394,"domain_scores_codex":[0.9981353,0.0003455618,0.0001946733,0.0004901888,0.0006925121,0.0001417773],"domain_scores_gemma":[0.993336,0.003112837,0.000473634,0.001497832,0.001401459,0.0001782663],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0003952886,0.000647286,0.02408255,0.0002495715,0.0001954106,0.0004074676,0.0002278092,0.1984831,0.009164783,0.007707037,0.009982267,0.7484575],"study_design_scores_gemma":[0.00001333372,0.00004944608,0.0009888938,0.00001323907,0.00002424424,0.00008135605,0.0000246342,0.9854239,0.003626819,0.007929966,0.001812915,0.00001122233],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03658892,0.0001463448,0.9567222,0.0001578676,0.0000638386,0.0002851468,0.0008159233,0.004397353,0.000822385],"genre_scores_gemma":[0.250254,0.0001503841,0.7428243,0.0001115949,0.0001027114,0.0007093362,0.003970083,0.000227777,0.001649839],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.00632715,"threshold_uncertainty_score":0.01532,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07602961379321414,"score_gpt":0.3056663072595603,"score_spread":0.2296366934663461,"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."}}