{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000516892,0.0001670222,0.0001701602,0.00008419116,0.0004155777,0.0003322782,0.0007283098,0.00007889634,0.00003213883],"category_scores_gemma":[0.0001185909,0.0001761111,0.0000695943,0.0004566047,0.0001614621,0.000224668,0.0001049382,0.0001610846,0.0001518305],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000391863,"about_ca_system_score_gemma":0.000136137,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007571967,"about_ca_topic_score_gemma":0.00001029296,"domain_scores_codex":[0.9983505,0.00002442565,0.0004137531,0.0005938055,0.0001831645,0.0004343389],"domain_scores_gemma":[0.9989048,0.000240138,0.0001408314,0.000516316,0.00008102364,0.0001168552],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000002194681,0.0000201674,0.000004127015,0.000003632995,0.000006616749,6.501213e-7,0.0001671487,0.0000849404,0.01065763,0.7338817,0.0001596809,0.2550115],"study_design_scores_gemma":[0.00009471117,0.00006407184,0.000003985664,0.0000193082,0.00002062881,0.00002886126,0.002423878,0.1646804,0.4047824,0.3830532,0.04421577,0.0006127645],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00312195,0.00001444442,0.9824697,0.0002097809,0.0005174284,0.0003450403,0.00001438759,0.0002121831,0.01309509],"genre_scores_gemma":[0.5897348,0.000003985199,0.409807,0.0001707335,0.0001020972,0.0001212663,0.000007560869,0.00001249573,0.00004008491],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5866128,"threshold_uncertainty_score":0.7181604,"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."}}