{"id":"W3173462463","doi":"10.1109/icpc52881.2021.00051","title":"Warning-Introducing Commits vs Bug-Introducing Commits: A tool, statistical models, and a preliminary user study","year":2021,"lang":"en","type":"article","venue":"","topic":"Software Engineering Research","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"","keywords":"Commit; Computer science; Logistic regression; Odds; Statistical model; Software bug; Predictive power; Software; Software engineering; Database; Machine learning; 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":[0.02791773,0.001778393,0.001304764,0.004055734,0.0008473283,0.002925761,0.002267525,0.001802539,0.003089378],"category_scores_gemma":[0.1384992,0.001251513,0.001375248,0.002838811,0.001115073,0.004763687,0.00272255,0.003089705,0.001180488],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009600085,"about_ca_system_score_gemma":0.0006896865,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004345573,"about_ca_topic_score_gemma":0.00642742,"domain_scores_codex":[0.9819285,0.01168902,0.001412832,0.002098795,0.002403468,0.0004673844],"domain_scores_gemma":[0.6283747,0.3303431,0.005694772,0.02074254,0.01292167,0.001923308],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.007118436,0.009302169,0.6266943,0.002078349,0.001052213,0.001984882,0.01943898,0.06603808,0.01555794,0.005210371,0.02660104,0.2189232],"study_design_scores_gemma":[0.0005983298,0.007752472,0.1287118,0.00035561,0.0003272019,0.001707976,0.00426531,0.8228398,0.01976572,0.004606755,0.00857754,0.0004914483],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.956214,0.0002845114,0.03483325,0.000389744,0.00004888,0.0004870966,0.002217528,0.00439612,0.00112889],"genre_scores_gemma":[0.9419582,0.0001205662,0.05185221,0.0001812433,0.00003727846,0.0006709825,0.00308392,0.001007902,0.001087659],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02791773,"threshold_uncertainty_score":0.1476448,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02113414477583096,"score_gpt":0.2742574760266623,"score_spread":0.2531233312508313,"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."}}