{"id":"W2537446610","doi":"10.1145/3001867.3001874","title":"Towards predicting feature defects in software product lines","year":2016,"lang":"en","type":"article","venue":"","topic":"Software Engineering Research","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Software bug; Software quality assurance; Software product line; Software quality; Naive Bayes classifier; Machine learning; Classifier (UML); Artificial intelligence; Data mining; Quality assurance; Software; Context (archaeology); Software development; Support vector machine; 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003813588,0.0001181556,0.0001155737,0.0001806812,0.00003323075,0.00007276073,0.0007568281,0.00005558379,0.00001476721],"category_scores_gemma":[0.004079562,0.0000728399,0.00003427601,0.0005957076,0.00002111324,0.0004301905,0.0003591854,0.0001531746,0.00005803325],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007692835,"about_ca_system_score_gemma":0.0001096831,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002741733,"about_ca_topic_score_gemma":0.00002156332,"domain_scores_codex":[0.9986861,0.00003253825,0.0001133582,0.0004295818,0.0003430686,0.0003953231],"domain_scores_gemma":[0.9987181,0.0005125563,0.00001879273,0.000569908,0.00009219665,0.00008845435],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.000004899895,0.00004536057,0.699071,0.00006090911,0.00001042371,0.00008225599,0.0003107808,0.0001198258,0.003052779,0.001202766,0.005791544,0.2902474],"study_design_scores_gemma":[0.0009691628,0.0001427891,0.9319848,0.0003740126,0.000002431327,0.00008306034,0.00000963576,0.003003452,0.05501371,0.001468574,0.006398762,0.0005495856],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.320516,0.0003322184,0.6725968,0.003908334,0.0005732107,0.0002694555,0.000001654261,0.001500009,0.0003023704],"genre_scores_gemma":[0.8891615,0.00001177071,0.1086959,0.00005691308,0.0001860215,0.00003066005,3.994711e-7,0.00001519431,0.001841737],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5686455,"threshold_uncertainty_score":0.4883912,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01581170763519573,"score_gpt":0.2604466243986399,"score_spread":0.2446349167634442,"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."}}