{"id":"W1507777432","doi":"10.1609/aimag.v32i2.2348","title":"AI‐Based Software Defect Predictors: Applications and Benefits in a Case Study","year":2011,"lang":"en","type":"article","venue":"AI Magazine","topic":"Software Engineering Research","field":"Computer Science","cited_by":67,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Process (computing); Software; Computer science; Software bug; Code (set theory); Reliability engineering; Software engineering; Software inspection; Predictive modelling; Software development; Machine learning; Artificial intelligence; Software quality; Engineering; Operating system; 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":[0.0003016416,0.0001272153,0.0001314247,0.0002501689,0.00005863718,0.00006304927,0.0003984574,0.00004391434,0.00001449862],"category_scores_gemma":[0.0001888764,0.0001243682,0.00002713074,0.0006888213,0.00003096947,0.0002503297,0.0002420849,0.000206566,0.00005522611],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003556986,"about_ca_system_score_gemma":0.00006082047,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001842199,"about_ca_topic_score_gemma":0.0002610364,"domain_scores_codex":[0.9989045,0.00004414212,0.0001665273,0.000404306,0.0002102903,0.0002701794],"domain_scores_gemma":[0.9988075,0.0003107591,0.00002187482,0.0006466574,0.00008536325,0.0001278313],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.000007115243,0.0005117876,0.9738318,0.00004034747,0.00002113295,0.001189114,0.001507885,0.0003063451,0.000014546,0.0002643247,0.0004871012,0.02181855],"study_design_scores_gemma":[0.00192357,0.0007504504,0.9802194,0.00004645024,0.00002007,0.0006419009,0.00005732442,0.01409567,0.0001934506,0.0003440381,0.001285229,0.0004224126],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5903893,0.0002494418,0.4078951,0.0001521201,0.0000524561,0.0007904302,0.000006262263,0.0004327025,0.00003226491],"genre_scores_gemma":[0.9827861,0.000002317661,0.01662457,0.000169722,0.00002428338,0.0003433492,0.000001784312,0.00001559209,0.00003228838],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3923968,"threshold_uncertainty_score":0.5071589,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03033593223569978,"score_gpt":0.272739207723545,"score_spread":0.2424032754878452,"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."}}