{"id":"W4319993380","doi":"10.1109/tnsm.2023.3239522","title":"LogEncoder: Log-Based Contrastive Representation Learning for Anomaly Detection","year":2023,"lang":"en","type":"article","venue":"IEEE Transactions on Network and Service Management","topic":"Software System Performance and Reliability","field":"Computer Science","cited_by":53,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"National Natural Science Foundation of China","keywords":"Computer science; Anomaly detection; Benchmark (surveying); Event (particle physics); Artificial intelligence; Data mining; Class (philosophy); Encoding (memory); Anomaly (physics); Representation (politics); Sequence (biology); Machine learning; Pattern recognition (psychology)","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":[0.001765923,0.001592501,0.001345935,0.001004493,0.0003855696,0.0007974834,0.001843553,0.001116725,0.001728243],"category_scores_gemma":[0.004944765,0.0004722331,0.0008794089,0.0009732415,0.0006981802,0.001886459,0.00110847,0.002827447,0.0009230803],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000877159,"about_ca_system_score_gemma":0.001135995,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005811435,"about_ca_topic_score_gemma":0.005775475,"domain_scores_codex":[0.9990319,0.0002642526,0.00006025492,0.0003161241,0.0002264943,0.0001009725],"domain_scores_gemma":[0.9983307,0.0009082169,0.0001477338,0.0002122371,0.0003523661,0.00004881602],"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":[0.0003862761,0.0006018479,0.003132223,0.000184166,0.0001968543,0.0001493319,0.00012359,0.3137586,0.01102751,0.004874113,0.01119504,0.6543704],"study_design_scores_gemma":[0.000007874491,0.00003555367,0.0002440162,0.000006067706,0.00000754453,0.00001997235,0.000005874767,0.9954666,0.001850073,0.001828909,0.00051973,0.000007686542],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02450324,0.0008462282,0.9685854,0.0002994341,0.0001104024,0.00007448729,0.0002948621,0.004312901,0.0009730112],"genre_scores_gemma":[0.5701934,0.0008285534,0.4187078,0.0005136452,0.0002025749,0.0003455705,0.002908922,0.0004404384,0.005859127],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005811435,"threshold_uncertainty_score":0.01155519,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0179370029405692,"score_gpt":0.2484519663164598,"score_spread":0.2305149633758906,"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."}}