{"id":"W3202359992","doi":"10.1145/3475716.3475790","title":"Continuous Software Bug Prediction","year":2021,"lang":"en","type":"article","venue":"","topic":"Software Engineering Research","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"","keywords":"Benchmark (surveying); Computer science; Software bug; Software; Software regression; Set (abstract data type); Data mining; Verification and validation; Software metric; Software development; Software evolution; Software engineering; Machine learning; Software quality; Software construction; Programming language; Engineering","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":[0.004028816,0.002005635,0.001110114,0.005243503,0.0005482111,0.001655578,0.002681511,0.001430535,0.001776508],"category_scores_gemma":[0.02706779,0.0004573135,0.0008870862,0.005247322,0.0007144998,0.00239243,0.001533992,0.001744989,0.001060938],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008091512,"about_ca_system_score_gemma":0.001490968,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005689537,"about_ca_topic_score_gemma":0.004521704,"domain_scores_codex":[0.9948859,0.001083972,0.000466067,0.001848539,0.001432833,0.0002827713],"domain_scores_gemma":[0.969494,0.01543883,0.005728923,0.003857439,0.004507452,0.0009732986],"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":[0.0007976191,0.001101876,0.2473201,0.003006799,0.0005459695,0.0004217168,0.0003360251,0.2222729,0.005703551,0.003167452,0.0463837,0.4689422],"study_design_scores_gemma":[0.0001630274,0.000969976,0.08623,0.0004289302,0.0001709513,0.0006556461,0.0001743414,0.8837501,0.004720909,0.01051451,0.01212637,0.0000952429],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7013421,0.01870086,0.2109751,0.002467969,0.0004431755,0.0006540743,0.04368835,0.01542974,0.006298599],"genre_scores_gemma":[0.8474561,0.002420824,0.09784088,0.0003136169,0.0003147723,0.0004807868,0.04962234,0.0002199998,0.001330628],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.005689537,"threshold_uncertainty_score":0.02130663,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0119914838602326,"score_gpt":0.2371583598666829,"score_spread":0.2251668760064503,"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."}}