{"id":"W4387974191","doi":"10.1002/nem.2251","title":"Assessing the impact of bag‐of‐words versus word‐to‐vector embedding methods and dimension reduction on anomaly detection from log files","year":2023,"lang":"en","type":"article","venue":"International Journal of Network Management","topic":"Software System Performance and Reliability","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"Intertek (Canada); Dalhousie University","funders":"","keywords":"Computer science; Dimensionality reduction; Benchmarking; Embedding; Word embedding; Word (group theory); Reduction (mathematics); Data mining; Dimension (graph theory); Encoder; Anomaly detection; Information retrieval; Natural language processing; Artificial intelligence","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":[0.001463681,0.00009509341,0.0001702665,0.0002433467,0.000072231,0.0001047958,0.0004340381,0.00003294395,0.000007306621],"category_scores_gemma":[0.00007154959,0.00006160799,0.0001245004,0.0004053142,0.00002807294,0.0003832435,0.0002288346,0.0001170087,0.000002356202],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001475721,"about_ca_system_score_gemma":0.00002102115,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006320059,"about_ca_topic_score_gemma":0.000001848744,"domain_scores_codex":[0.9986588,0.00017963,0.0004413088,0.0001599338,0.0004388761,0.0001214822],"domain_scores_gemma":[0.9986749,0.0004120647,0.0004744187,0.0001960592,0.0002034771,0.00003913239],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0003184046,0.00005293704,0.0021912,0.00001646405,0.0005970336,0.00001374749,0.0006497047,0.4600617,0.00213235,0.0002383462,0.0008564816,0.5328717],"study_design_scores_gemma":[0.001352802,0.0009146883,0.6724493,0.001033453,0.00008418912,0.00003817019,0.0005898093,0.3150092,0.003821058,0.003994797,0.0004954174,0.0002171393],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8001966,0.00007397171,0.1956685,0.0002380503,0.003625816,0.00009946711,0.000001045927,0.00001837585,0.00007808166],"genre_scores_gemma":[0.966529,0.00008847628,0.03290974,0.00001209822,0.0004390206,0.000003007866,0.000001266596,0.000005311694,0.00001209963],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6702581,"threshold_uncertainty_score":0.2512301,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03230924128243456,"score_gpt":0.3986022229203495,"score_spread":0.3662929816379149,"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."}}