{"id":"W4281675176","doi":"10.36227/techrxiv.19498769.v1","title":"Detecting Anomalies in Logs by Combining NLP features with Embedding or TF-IDF","year":2022,"lang":"en","type":"preprint","venue":"","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Lakehead University","funders":"Lakehead University","keywords":"Categorization; Computer science; Artificial intelligence; Natural language processing; Sentence; Set (abstract data type); Focus (optics); Embedding; Text categorization; Information retrieval","routes":{"ca_aff":true,"ca_fund":true,"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":[0.001504076,0.001171442,0.00107814,0.007362155,0.0004201366,0.001540517,0.0007643274,0.001040087,0.001456696],"category_scores_gemma":[0.007381566,0.000217048,0.0007120852,0.004377186,0.0004481246,0.003295289,0.000687081,0.0009508414,0.002154799],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004414319,"about_ca_system_score_gemma":0.0004117427,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002607158,"about_ca_topic_score_gemma":0.002913876,"domain_scores_codex":[0.9985385,0.0002218997,0.0002033008,0.0003545102,0.0005428646,0.0001389081],"domain_scores_gemma":[0.9944213,0.002622419,0.001024208,0.000643015,0.001125218,0.0001638626],"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":[0.0007294377,0.0007244693,0.05202716,0.0005684622,0.0001572303,0.0005433359,0.0004662396,0.01490063,0.06837259,0.001562196,0.008382332,0.8515659],"study_design_scores_gemma":[0.00004956369,0.0007512852,0.06458491,0.0001096168,0.0001457554,0.001543984,0.0008276204,0.858027,0.04971928,0.01179254,0.01229097,0.0001574131],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.2688749,0.001308528,0.705242,0.0007628439,0.0004411179,0.0004090791,0.006313885,0.01351789,0.003129764],"genre_scores_gemma":[0.6291465,0.0005029268,0.3593641,0.0001104678,0.0003003136,0.0002751003,0.008024781,0.0003835955,0.001892257],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.007362155,"threshold_uncertainty_score":0.007954419,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0231594513300244,"score_gpt":0.2890592490640066,"score_spread":0.2658997977339822,"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."}}