{"id":"W2396100201","doi":"10.1109/saner.2016.113","title":"The Impact of Human Discussions on Just-in-Time Quality Assurance: An Empirical Study on OpenStack and Eclipse","year":2016,"lang":"en","type":"article","venue":"","topic":"Software Engineering Research","field":"Computer Science","cited_by":29,"is_retracted":false,"has_abstract":true,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Computer science; Eclipse; Source lines of code; Variety (cybernetics); Process (computing); Quality (philosophy); Recall; Relation (database); Logistic regression; Code review; Feeling; Empirical research; Data science; Machine learning; Data mining; Artificial intelligence; Software quality; Psychology; Cognitive psychology; Programming language; Statistics; Software; Software development; Social psychology","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":[0.001453114,0.0001170301,0.0001776283,0.00008808565,0.000122257,0.0001083061,0.0008775558,0.00003488686,0.0000360684],"category_scores_gemma":[0.0007472886,0.00004501921,0.00004378329,0.0002523543,0.00006956676,0.0002179993,0.000280805,0.0001385224,0.0000367492],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000776924,"about_ca_system_score_gemma":0.00004948406,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001153522,"about_ca_topic_score_gemma":0.00005199292,"domain_scores_codex":[0.9983293,0.000338928,0.0002286975,0.0003442432,0.000479778,0.0002790963],"domain_scores_gemma":[0.9963703,0.002476811,0.00003476267,0.0009356834,0.00004427783,0.0001381754],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00005533027,0.001118733,0.9817798,0.000004116354,0.00002690853,0.00001154916,0.001441149,0.0001015852,0.002036283,0.001397132,0.002730599,0.009296835],"study_design_scores_gemma":[0.0005574903,0.001371644,0.9970331,0.00002462599,7.483078e-7,6.869294e-7,0.00006610309,0.0003464884,0.000214263,0.0002820155,0.00001323363,0.00008957712],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9974429,0.000002576356,0.001022825,0.0007173611,0.00004196645,0.0002962556,0.000003389341,0.0000645419,0.0004081635],"genre_scores_gemma":[0.9991784,0.000001740978,0.0001292865,0.00001343721,0.00003326267,0.0000124419,1.960392e-7,0.000007253044,0.0006239594],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01525335,"threshold_uncertainty_score":0.183583,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08834997096515398,"score_gpt":0.4534448587385435,"score_spread":0.3650948877733895,"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."}}