{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000388742,0.0003277968,0.0003699004,0.0004294646,0.0002510723,0.0006500525,0.002212646,0.0002222634,0.0001783769],"category_scores_gemma":[0.0001192944,0.0002498264,0.00005806075,0.0006281323,0.00008485848,0.0003636097,0.003698707,0.001135651,0.000006915786],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001969712,"about_ca_system_score_gemma":0.0001547038,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002054101,"about_ca_topic_score_gemma":0.0001669518,"domain_scores_codex":[0.9978246,0.00008769385,0.0003697719,0.0009119131,0.0004029912,0.0004030373],"domain_scores_gemma":[0.998305,0.0002516708,0.0003208268,0.00103877,0.00003982968,0.00004386354],"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":[0.0003168774,0.0008796337,0.06826885,0.0008847803,0.0004328461,0.0005340784,0.01667202,0.01565856,0.004475134,0.2886839,0.0475863,0.555607],"study_design_scores_gemma":[0.01190061,0.006156967,0.04719876,0.003377283,0.0002184829,0.0006998911,0.1070073,0.3711201,0.15896,0.1573383,0.1186833,0.01733905],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2665558,0.00201178,0.6792967,0.009459996,0.00170544,0.00174834,0.0000230744,0.008243693,0.03095525],"genre_scores_gemma":[0.9113147,0.0000579003,0.0830125,0.0002100531,0.00001511844,0.0002553301,0.00001722947,0.00002343622,0.005093749],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6447589,"threshold_uncertainty_score":0.9999954,"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."}}