{"id":"W4384302785","doi":"10.1109/icse48619.2023.00063","title":"Explaining Software Bugs Leveraging Code Structures in Neural Machine Translation","year":2023,"lang":"en","type":"preprint","venue":"","topic":"Software Engineering Research","field":"Computer Science","cited_by":24,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dalhousie University","funders":"Dalhousie University","keywords":"Computer science; Software bug; Leverage (statistics); Source code; Machine translation; Code review; Software; Code (set theory); Artificial intelligence; Software engineering; Security bug; Machine learning; Programming language; Static program analysis; Software development; Software security assurance; Computer security","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001251437,0.001210947,0.0004970263,0.002413907,0.0005640715,0.0009538734,0.001292016,0.001806444,0.003799473],"category_scores_gemma":[0.01153622,0.0005699155,0.001303655,0.001601938,0.0007129268,0.002237977,0.001197715,0.001759473,0.001766993],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001088347,"about_ca_system_score_gemma":0.001333638,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006133088,"about_ca_topic_score_gemma":0.01211935,"domain_scores_codex":[0.9990361,0.0003676876,0.00005736182,0.0002886112,0.0001909121,0.00005929397],"domain_scores_gemma":[0.9934076,0.005070387,0.0003487153,0.0005882969,0.000502724,0.00008226123],"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":[0.0003931376,0.0003656535,0.01083571,0.0009488167,0.0001712181,0.001565185,0.001186814,0.1897986,0.0158354,0.01591266,0.02064905,0.7423378],"study_design_scores_gemma":[0.00005396845,0.00009067265,0.001146923,0.00006686872,0.00006145607,0.0003326056,0.0001120351,0.9605417,0.006329042,0.02694675,0.004289937,0.00002822692],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1656281,0.002542775,0.7952611,0.002170851,0.0003229102,0.0003333759,0.002166387,0.02502063,0.006553796],"genre_scores_gemma":[0.7266366,0.0009690223,0.2612956,0.0005296465,0.0001263838,0.0001991731,0.005536374,0.0009115093,0.003795657],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006133088,"threshold_uncertainty_score":0.01271051,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08106133440923918,"score_gpt":0.3153356945573667,"score_spread":0.2342743601481275,"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."}}