{"id":"W2051978688","doi":"10.1109/icsm.2010.5609530","title":"Revisiting common bug prediction findings using effort-aware models","year":2010,"lang":"en","type":"article","venue":"","topic":"Software Engineering Research","field":"Computer Science","cited_by":208,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"","keywords":"Computer science; Predictive modelling; Eclipse; Software bug; Software quality; Process (computing); Software quality assurance; Quality (philosophy); Code (set theory); Software engineering; Machine learning; Data mining; Software; Software development; Programming language; Set (abstract data type)","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":[0.0004808737,0.0001073769,0.0001149011,0.0001454596,0.0001547837,0.0002063109,0.0006244312,0.00008643046,0.00002473971],"category_scores_gemma":[0.0001146641,0.0001028319,0.00004311868,0.0003684909,0.00002228912,0.0008197618,0.0003130844,0.0004046386,0.00002224313],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004692723,"about_ca_system_score_gemma":0.00004284647,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007774679,"about_ca_topic_score_gemma":0.000003029522,"domain_scores_codex":[0.9988263,0.00001300379,0.0001772569,0.0002993458,0.0003595339,0.0003245621],"domain_scores_gemma":[0.999034,0.0002236662,0.00002522167,0.0005227239,0.00008457961,0.0001098298],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0000137304,0.0001250604,0.576982,0.0003719595,0.00009418093,0.0001249709,0.002094747,0.1516963,0.07900047,0.09968814,0.002407283,0.08740121],"study_design_scores_gemma":[0.0001020717,0.00001214325,0.01102723,0.00003371613,0.000001987984,0.00003844044,0.000004930329,0.9845131,0.003252717,0.0007553322,0.0001472089,0.0001111309],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4694573,0.000007998123,0.5293528,0.00007343498,0.0002690137,0.00007228595,9.537908e-7,0.000461756,0.0003044543],"genre_scores_gemma":[0.9373237,0.000001834253,0.06234672,0.0000359709,0.0001526504,0.000005606141,0.000002113799,0.00001372419,0.0001176656],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8328168,"threshold_uncertainty_score":0.4193362,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03014153758873253,"score_gpt":0.2827906679676374,"score_spread":0.2526491303789048,"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."}}