{"id":"W7117313584","doi":"10.1007/s10115-025-02657-2","title":"Enhanced software defect prediction using edge feature and self-attention GAN with pelican optimization","year":2025,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Software Engineering Research","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Feature (linguistics); Convolutional neural network; Software; Enhanced Data Rates for GSM Evolution; Artificial neural network; Software bug; Pattern recognition (psychology); Software system; Deep learning","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":[0.0002961569,0.0001164397,0.0001265631,0.0003340668,0.0001887015,0.0004383021,0.0001329424,0.00008987611,4.331284e-7],"category_scores_gemma":[0.0001093614,0.0001002877,0.00001712241,0.0007253024,0.00001855987,0.002557725,0.00007296375,0.0001084891,0.000004735399],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009827519,"about_ca_system_score_gemma":0.0001024407,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009069001,"about_ca_topic_score_gemma":0.00000138261,"domain_scores_codex":[0.9992653,0.00004489041,0.0002025628,0.0001601879,0.000171858,0.0001552238],"domain_scores_gemma":[0.9991679,0.0000965494,0.00007527798,0.000206357,0.0003919999,0.00006188146],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002008835,0.0004743965,0.1902836,0.0156125,0.001081998,0.000006651125,0.04692124,0.489338,0.002416472,0.03375196,0.01396118,0.205951],"study_design_scores_gemma":[0.0006617949,0.0000933604,0.02084721,0.0003989053,0.00002035311,0.00003546141,0.000153226,0.97223,0.0002743845,0.000003811143,0.005122651,0.0001588513],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03734818,0.0005858695,0.9600637,0.00002642883,0.0003529969,0.0003811351,0.00000377835,0.0003921784,0.0008457626],"genre_scores_gemma":[0.9881092,0.00007270918,0.01152947,0.000017533,0.00005174366,0.00004480134,0.00002784032,0.000006090218,0.0001405943],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.950761,"threshold_uncertainty_score":0.4226557,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.006036464635271571,"score_gpt":0.2296626946988261,"score_spread":0.2236262300635545,"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."}}