{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004921123,0.001409266,0.0008968911,0.002674517,0.0004434133,0.001463647,0.0008900405,0.001029236,0.0008873313],"category_scores_gemma":[0.02507494,0.0002470138,0.0007241426,0.001710297,0.0006824346,0.002799292,0.00116267,0.001215911,0.0006080255],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005604316,"about_ca_system_score_gemma":0.0007189884,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004933737,"about_ca_topic_score_gemma":0.003811165,"domain_scores_codex":[0.9965807,0.001661069,0.0003303495,0.0004722808,0.0007279629,0.0002276375],"domain_scores_gemma":[0.9811592,0.01371838,0.0008589157,0.001319342,0.002627133,0.000317072],"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":[0.002231235,0.001711518,0.03213031,0.0006326984,0.0005692198,0.000236099,0.0003377211,0.3659817,0.02326244,0.002129123,0.004894085,0.5658838],"study_design_scores_gemma":[0.00002958151,0.0007950928,0.007466706,0.00003319541,0.00005311648,0.0001057858,0.0002060935,0.9706467,0.01885672,0.001111823,0.0006554429,0.00003977417],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8708231,0.001033639,0.122142,0.0003704684,0.0002018572,0.0001572745,0.0008830206,0.002947279,0.001441437],"genre_scores_gemma":[0.9111986,0.0002447986,0.08544916,0.00006041631,0.00004217364,0.00011531,0.002050711,0.0001610701,0.0006777686],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.004933737,"threshold_uncertainty_score":0.02602571,"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."}}