{"id":"W4389495064","doi":"10.2139/ssrn.4658344","title":"Aml: An Accuracy Metric Model for Effective Evaluation of Log Parsing Techniques","year":2023,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Software System Performance and Reliability","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Concordia University","funders":"","keywords":"Metric (unit); Parsing; Computer science; Statistics; Mathematics; Natural language processing; Engineering; Operations management","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01967635,0.000285178,0.000503062,0.0006409183,0.0002229658,0.0001429195,0.001378144,0.0003462825,6.981878e-7],"category_scores_gemma":[0.001002878,0.0002405467,0.0003364513,0.000547947,0.00004388531,0.0006551325,0.0003904753,0.002062503,0.000002977162],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002534969,"about_ca_system_score_gemma":0.007156793,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008780244,"about_ca_topic_score_gemma":0.0001197475,"domain_scores_codex":[0.9958588,0.0004743321,0.0006910726,0.0006126648,0.0009495983,0.001413496],"domain_scores_gemma":[0.9964661,0.0004090162,0.0008758752,0.0008242658,0.001346781,0.00007793764],"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":[0.00006042841,0.0001703507,0.0007684224,0.0003159014,0.0003384861,4.500329e-7,0.001078285,0.102274,0.00016611,0.00989818,0.00007058495,0.8848588],"study_design_scores_gemma":[0.0002487984,0.0002789828,0.0003094764,0.0001337475,0.00009273721,0.00002559889,0.00005348858,0.5618471,0.0008046239,0.436038,0.000005443624,0.0001619829],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1080682,0.001435343,0.8876718,0.0001656846,0.0006631398,0.001726023,0.000006832205,0.0002382607,0.0000247238],"genre_scores_gemma":[0.9847679,0.001143242,0.01335754,0.00001427302,0.0002834282,0.0003489974,0.00001370224,0.00003423024,0.00003670746],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8846968,"threshold_uncertainty_score":0.9984717,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05219061129629513,"score_gpt":0.3627940116875584,"score_spread":0.3106034003912633,"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."}}