{"id":"W4384158990","doi":"10.1109/icpc58990.2023.00023","title":"Towards a Classification of Log Parsing Errors","year":2023,"lang":"en","type":"article","venue":"","topic":"Software System Performance and Reliability","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Brock University; Concordia University","funders":"","keywords":"Parsing; Debugging; Computer science; Key (lock); Artificial intelligence; Bottom-up parsing; S-attributed grammar; Point (geometry); Data mining; Top-down parsing; Natural language processing; Programming language","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":[0.0003908439,0.0000446514,0.00008506826,0.00007883472,0.00004009979,0.00001543039,0.00027077,0.00003836714,0.000008810463],"category_scores_gemma":[0.00003704104,0.0000328949,0.00003880466,0.0006562868,0.00002853726,0.0002013955,0.00007782523,0.00003417328,0.00015006],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001860958,"about_ca_system_score_gemma":0.00005510751,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004223043,"about_ca_topic_score_gemma":0.000003318147,"domain_scores_codex":[0.9993598,0.00002361457,0.0001729989,0.0001577914,0.0001667287,0.0001190949],"domain_scores_gemma":[0.999514,0.00003334608,0.00004906216,0.0003151329,0.00006083624,0.00002755657],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.00001175168,0.0001470519,0.1571135,0.0004024562,0.00003728339,0.000006027743,0.005059207,0.0004523438,0.01096113,0.07263412,0.0144881,0.738687],"study_design_scores_gemma":[0.0001949562,0.00006727187,0.7231362,0.00004188831,0.000003139545,0.000004917046,0.0002521687,0.2615261,0.008015365,0.004092325,0.002518553,0.0001471278],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6557935,0.00001734942,0.3334707,0.001480245,0.0005743939,0.0001239637,6.016168e-7,0.0005978116,0.007941413],"genre_scores_gemma":[0.9947307,0.000006682672,0.004970408,0.00003165382,0.00001720915,0.000006059024,0.000001239472,0.000002152454,0.0002338667],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7385399,"threshold_uncertainty_score":0.1928768,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04534853469578359,"score_gpt":0.2943115432125853,"score_spread":0.2489630085168018,"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."}}