{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005828458,0.0003281564,0.0003348789,0.0007136147,0.00007296632,0.0003767524,0.001652711,0.0002284404,0.00003588496],"category_scores_gemma":[0.000536253,0.0003319393,0.0001029441,0.0005669407,0.000023635,0.0002819738,0.001356807,0.00133822,0.00003043511],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000150257,"about_ca_system_score_gemma":0.0001317448,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006543638,"about_ca_topic_score_gemma":0.0001996913,"domain_scores_codex":[0.997385,0.00009722949,0.0003999789,0.0009069418,0.0006603245,0.0005505821],"domain_scores_gemma":[0.9976597,0.001216099,0.00006707278,0.0008881954,0.00005985575,0.0001091154],"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":[0.000008825713,0.00001600654,0.04962784,0.0003165353,0.00003606453,0.0002062283,0.004069978,0.7190101,0.00004640897,0.0004037611,0.0003963379,0.225862],"study_design_scores_gemma":[0.000265478,0.00001378745,0.0749218,0.0001171763,0.000002562054,0.00001048464,0.0000200826,0.9207844,0.0001163401,0.003297705,0.00007639631,0.000373819],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03692345,0.0007841602,0.9574131,0.0007822081,0.001328351,0.0003529305,0.00001665142,0.00235806,0.00004108514],"genre_scores_gemma":[0.8346663,0.00002100349,0.1648211,0.00005764885,0.00009595859,0.0000605434,0.00005570444,0.00005516556,0.0001666492],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7977428,"threshold_uncertainty_score":0.9999133,"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."}}