{"id":"W2034259517","doi":"10.1145/1540438.1540453","title":"Practical considerations in deploying AI for defect prediction","year":2009,"lang":"en","type":"article","venue":"","topic":"Software Engineering Research","field":"Computer Science","cited_by":63,"is_retracted":false,"has_abstract":true,"ca_institutions":"National Research Council Canada","funders":"Türkiye Bilimsel ve Teknolojik Araştırma Kurumu; National Aeronautics and Space Administration","keywords":"Computer science; Software bug; Software quality; Code (set theory); Software; Quality (philosophy); Software engineering; Software development; 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":[0.02489247,0.00153777,0.001088946,0.001917039,0.000980322,0.004701774,0.004047441,0.002753442,0.005474579],"category_scores_gemma":[0.08380586,0.001008412,0.0005215572,0.001987703,0.001467503,0.0068698,0.001854204,0.002875718,0.002936282],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009362306,"about_ca_system_score_gemma":0.002346174,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01024605,"about_ca_topic_score_gemma":0.008120298,"domain_scores_codex":[0.9781139,0.01610358,0.0009330365,0.001439185,0.00280395,0.0006062873],"domain_scores_gemma":[0.8216308,0.1398235,0.002511301,0.01185954,0.02161335,0.002561429],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.002034463,0.001703773,0.06614448,0.001624303,0.0002979556,0.001810408,0.003354198,0.1067389,0.03121503,0.01480591,0.01992141,0.7503492],"study_design_scores_gemma":[0.0006677551,0.002952349,0.03183771,0.00097961,0.000264543,0.001819851,0.01120168,0.8352176,0.01991168,0.0437719,0.05106932,0.0003060849],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2765527,0.004956529,0.6117314,0.05124551,0.000838396,0.002115875,0.0005953833,0.01238067,0.03958359],"genre_scores_gemma":[0.5437853,0.001004213,0.4492756,0.001162065,0.0002706732,0.0005625751,0.0003662045,0.00040238,0.003171059],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.02489247,"threshold_uncertainty_score":0.1316455,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05020378970394145,"score_gpt":0.3554216176059663,"score_spread":0.3052178279020248,"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."}}