{"id":"W4388212665","doi":"10.1109/issre59848.2023.00037","title":"Using Transformer Models and Textual Analysis for Log Parsing","year":2023,"lang":"en","type":"article","venue":"","topic":"Software System Performance and Reliability","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Polytechnique Montréal","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Parsing; Computer science; Cluster analysis; S-attributed grammar; Vocabulary; Artificial intelligence; Natural language processing; Data mining","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":[0.0003973934,0.00007519092,0.0001634929,0.0001862357,0.0001544716,0.00007364617,0.000159933,0.00004776789,0.000002973886],"category_scores_gemma":[0.000006899615,0.00005585366,0.0000998873,0.001019059,0.00002711752,0.0004828759,0.00002797614,0.00003099686,0.000004756843],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001731444,"about_ca_system_score_gemma":0.00002921275,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007421854,"about_ca_topic_score_gemma":0.00002143421,"domain_scores_codex":[0.999218,0.00001410862,0.000167328,0.0002630301,0.000118432,0.0002191331],"domain_scores_gemma":[0.9995703,0.00008848908,0.00002259206,0.0002215582,0.00004655961,0.00005049144],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00005344192,0.0001396192,0.113727,0.0006027555,0.001361816,0.000009360921,0.01225302,0.5482829,0.00278354,0.06406977,0.001215475,0.2555013],"study_design_scores_gemma":[0.0001410381,0.0000190519,0.002193196,0.000005571412,0.00004433033,0.000002265427,0.000096291,0.9935974,0.0003114606,0.003394349,0.0001031112,0.00009193447],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2115723,0.00002523904,0.787574,0.0001466078,0.00006319144,0.0001276321,0.000002192279,0.0001757479,0.000313087],"genre_scores_gemma":[0.9642369,0.00001227497,0.03554499,0.00006338181,0.00002210964,0.000009280851,0.000002718068,0.000003489291,0.0001048596],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7526646,"threshold_uncertainty_score":0.2277646,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09670691870942685,"score_gpt":0.3208775355005888,"score_spread":0.2241706167911619,"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."}}