{"id":"W3196824794","doi":"10.1109/ase51524.2021.9678596","title":"Leveraging Code Clones and Natural Language Processing for Log Statement Prediction","year":2021,"lang":"en","type":"article","venue":"2021 36th IEEE/ACM International Conference on Automated Software Engineering (ASE)","topic":"Software System Performance and Reliability","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Source code; Statement (logic); Debugging; Java; Context (archaeology); Programming language; Data mining; Database; Artificial intelligence; Information retrieval","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003428814,0.0002698899,0.0002553904,0.000173008,0.0001598211,0.0003954318,0.0005480698,0.0001066129,0.00003935833],"category_scores_gemma":[0.0006196731,0.0002586234,0.00007581462,0.0002428675,0.00002857641,0.0005665182,0.0001798918,0.0002488549,0.00001525576],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002072915,"about_ca_system_score_gemma":0.000238568,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001572753,"about_ca_topic_score_gemma":0.00000524229,"domain_scores_codex":[0.9980912,0.00003796307,0.0004549387,0.0006188623,0.0004549575,0.000342064],"domain_scores_gemma":[0.9985705,0.0002042939,0.0001372812,0.000441984,0.0005393759,0.0001065838],"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":[0.0004896024,0.001700616,0.05672396,0.007427888,0.00221477,0.00126167,0.03422398,0.2169444,0.08401684,0.01472998,0.01858834,0.5616779],"study_design_scores_gemma":[0.0006888503,0.00006241144,0.006659476,0.0005363778,0.00001365512,0.00006356512,0.0001788826,0.98361,0.006553419,0.00009085777,0.001229652,0.0003129044],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2915133,0.0006711504,0.6995513,0.001064911,0.004493271,0.0004239236,0.0001755043,0.002057274,0.00004936962],"genre_scores_gemma":[0.9488178,0.00006262775,0.05018332,0.0001349939,0.0001962589,0.00009517954,0.0001885563,0.00002529624,0.000295938],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7666655,"threshold_uncertainty_score":0.9999866,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02070793589757158,"score_gpt":0.2854924140753931,"score_spread":0.2647844781778215,"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."}}