{"id":"W4400391016","doi":"10.1016/j.jss.2024.112154","title":"AML: An accuracy metric model for effective evaluation of log parsing techniques","year":2024,"lang":"en","type":"article","venue":"Journal of Systems and Software","topic":"Software System Performance and Reliability","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada; Ministère de la Défense Nationale; Innovation for Defence Excellence and Security","keywords":"Parsing; Computer science; Metric (unit); Debugging; Data mining; Software; Task (project management); Artificial intelligence; Programming language","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":[],"consensus_categories":[],"category_scores_codex":[0.004640499,0.0001114386,0.0003390837,0.0003406724,0.00008165385,0.0001720405,0.0002504089,0.0001001373,4.349051e-7],"category_scores_gemma":[0.0005538087,0.00007565774,0.0001225146,0.0003490118,0.00002769509,0.001225261,0.00003824055,0.0001256099,3.372817e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001237966,"about_ca_system_score_gemma":0.000248679,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000226525,"about_ca_topic_score_gemma":0.000001189061,"domain_scores_codex":[0.998419,0.0001597281,0.0005727668,0.0001913265,0.0005253769,0.0001318201],"domain_scores_gemma":[0.997752,0.0005432854,0.000350283,0.0002271767,0.001054354,0.00007289029],"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":[0.00004564767,0.0001106377,0.004681765,0.003096467,0.0001696075,0.000006381601,0.004551579,0.01875309,0.0005215016,0.001179503,0.0006524334,0.9662314],"study_design_scores_gemma":[0.0003068876,0.0005125387,0.001377075,0.001191339,0.00009596717,0.0001561633,0.0001207148,0.9920313,0.0007702541,0.003038781,0.0002801357,0.0001187927],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2195211,0.007292127,0.7718188,0.00003310372,0.000671974,0.0005823793,0.00000582017,0.00006644272,0.000008363302],"genre_scores_gemma":[0.977806,0.00007823082,0.02187693,0.00000793969,0.0001736763,0.00003858168,7.572795e-7,0.000009000169,0.000008885325],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9732783,"threshold_uncertainty_score":0.3085233,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03965729576152576,"score_gpt":0.3410378737279783,"score_spread":0.3013805779664525,"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."}}