{"id":"W2523412570","doi":"10.1145/2961111.2962601","title":"Predicting Defectiveness of Software Patches","year":2016,"lang":"en","type":"article","venue":"","topic":"Software Engineering Research","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Code review; Computer science; Software quality; Context (archaeology); Code (set theory); Software engineering; Process (computing); Software; Reliability engineering; Programming language; Software development; Engineering; Geology","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":[],"consensus_categories":[],"category_scores_codex":[0.0002315957,0.00005438324,0.00007819716,0.00006879793,0.00002078698,0.00001413195,0.0004862499,0.00002779535,0.00002046668],"category_scores_gemma":[0.001283776,0.00003361625,0.00003225918,0.0002109757,0.00002655758,0.0002376901,0.0002255212,0.00003465189,0.00002366208],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000027946,"about_ca_system_score_gemma":0.00004248801,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002644059,"about_ca_topic_score_gemma":0.000002384108,"domain_scores_codex":[0.9993216,0.00002167098,0.0000956457,0.0001743921,0.0002156279,0.0001710817],"domain_scores_gemma":[0.9980336,0.001458955,0.00002130114,0.0003478842,0.0000906635,0.00004764003],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.000001467932,0.00001513495,0.9100136,0.00002062398,0.00001009258,0.000002792327,0.0001094085,0.00002838686,0.00387481,0.002250474,0.00005337809,0.08361983],"study_design_scores_gemma":[0.000421991,0.0001149455,0.8219482,0.0001421098,0.000002025934,0.00001076593,0.00001247876,0.001251199,0.1729584,0.002697576,0.0002551008,0.000185217],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3214845,0.00002138694,0.6779631,0.00006063004,0.00007571225,0.00003671389,7.629149e-7,0.0002783181,0.00007887328],"genre_scores_gemma":[0.9564241,0.000002519442,0.04335434,0.000005954294,0.00001851341,0.000008333871,5.573227e-8,0.000005633025,0.0001805505],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6349396,"threshold_uncertainty_score":0.1536893,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01556609008021599,"score_gpt":0.2453293019712046,"score_spread":0.2297632118909887,"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."}}