{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003013767,0.00004329559,0.00005144506,0.000106766,0.00004840129,0.0001120497,0.00006353352,0.00003218033,0.000007322199],"category_scores_gemma":[0.002497579,0.00004160286,0.00002645638,0.0001796884,0.000006086413,0.0004318674,0.00002176104,0.000108557,0.00001027732],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004432325,"about_ca_system_score_gemma":0.0000839059,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005232193,"about_ca_topic_score_gemma":0.000008617529,"domain_scores_codex":[0.9994136,0.00002029323,0.0001013919,0.0001694616,0.0001256625,0.0001695741],"domain_scores_gemma":[0.9984162,0.001300317,0.000007814673,0.0001775647,0.00005427648,0.00004377536],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001252337,0.000325923,0.03996654,0.00002594889,0.00002324178,0.00009074557,0.0005990083,0.009932358,0.002776352,0.8675299,0.06274889,0.01596855],"study_design_scores_gemma":[0.0008852598,0.0003821158,0.1535437,0.00002443449,0.000004210209,0.0001585928,0.00001076273,0.80096,0.004722393,0.03775656,0.001351033,0.0002010127],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005963715,0.00001229866,0.9868077,0.006406705,0.00008933285,0.0002078312,4.551456e-7,0.00033501,0.0001769633],"genre_scores_gemma":[0.7633965,7.934542e-7,0.2361501,0.000372252,0.0000248947,0.00002414532,4.929144e-7,0.000002512515,0.00002828836],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8297734,"threshold_uncertainty_score":0.2990015,"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."}}