{"id":"W4235705087","doi":"10.32920/ryerson.14648622","title":"On Empirically Examining The Effectiveness Of Deep Learning-Based Bug Localization Models","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Software Engineering Research","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Computer science; Software bug; Java; Set (abstract data type); Software; Artificial intelligence; Convolutional neural network; Deep learning; Baseline (sea); Convolution (computer science); Machine learning; Software engineering; State (computer science); Artificial neural network; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01244145,0.003170118,0.001360268,0.002049657,0.0008445128,0.002119503,0.00222269,0.003560991,0.001864025],"category_scores_gemma":[0.06067461,0.000889765,0.0009982137,0.001873394,0.001575028,0.006096322,0.001774545,0.003672048,0.0007127594],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003158042,"about_ca_system_score_gemma":0.001840037,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02170361,"about_ca_topic_score_gemma":0.0213879,"domain_scores_codex":[0.9954227,0.00219255,0.0004475129,0.0008661835,0.0007376974,0.0003333295],"domain_scores_gemma":[0.9391235,0.04854934,0.002910136,0.003895964,0.004634511,0.0008865882],"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":[0.001432692,0.001236302,0.04046419,0.0008767899,0.0006226913,0.0001440449,0.0001857336,0.8432648,0.002252136,0.003128658,0.007070777,0.09932121],"study_design_scores_gemma":[0.00008840155,0.0006729994,0.003501026,0.000146479,0.0001484429,0.00006563409,0.00009620473,0.9891777,0.002411981,0.002928714,0.0007307582,0.00003162811],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9066384,0.008643059,0.0666111,0.003691472,0.0003315026,0.0002549636,0.00218075,0.002159314,0.009489511],"genre_scores_gemma":[0.9724978,0.001058041,0.02262434,0.0003723246,0.00006445728,0.00009948421,0.002216339,0.00009136518,0.0009758918],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02170361,"threshold_uncertainty_score":0.06579739,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0332308554420437,"score_gpt":0.2871205612570827,"score_spread":0.253889705815039,"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."}}