{"id":"W4375824997","doi":"10.1007/978-3-031-28332-1_5","title":"A Two-Step Approach to Boost Neural Network Generalizability in Predicting Defective Software","year":2023,"lang":"en","type":"book-chapter","venue":"Advances in intelligent systems and computing","topic":"Software Engineering Research","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Verafin (Canada)","funders":"","keywords":"Generalizability theory; Computer science; Artificial neural network; Machine learning; Software; Artificial intelligence; Software metric; Java; Quality (philosophy); Software quality; Data mining; Software engineering; Software development; Programming language; Statistics","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001681118,0.0005200257,0.0007966739,0.0004956279,0.0001496223,0.0002541478,0.0009718385,0.0002150005,8.910115e-7],"category_scores_gemma":[0.0005016046,0.0005372344,0.0001111027,0.0005418572,0.00006555881,0.0002909788,0.001328104,0.0008936857,0.00001729079],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004074432,"about_ca_system_score_gemma":0.00006385311,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003447155,"about_ca_topic_score_gemma":0.0001359004,"domain_scores_codex":[0.9960213,0.0001437665,0.0009732064,0.001386559,0.0006019671,0.0008732479],"domain_scores_gemma":[0.9966049,0.002108827,0.000233214,0.0007199604,0.0001335843,0.0001995696],"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":[0.000008564315,0.00001829822,0.03245743,0.000467696,0.00002433163,0.00004963439,0.0007429172,0.8855689,3.358509e-7,0.04598977,0.00004723014,0.03462493],"study_design_scores_gemma":[0.0002651626,0.0001299992,0.001973465,0.002334334,0.000007000414,0.00006675228,0.0001208453,0.9868662,0.000002372416,0.002746316,0.004685423,0.0008021417],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002719013,0.01248468,0.9722954,0.00001919813,0.002853567,0.001666829,0.000009240387,0.0006839272,0.007268118],"genre_scores_gemma":[0.8087741,0.00182484,0.1697942,0.0002759827,0.003598186,0.0005891514,0.00006790443,0.0005786734,0.01449694],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8060551,"threshold_uncertainty_score":0.9997079,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02767367682521481,"score_gpt":0.2816586271396522,"score_spread":0.2539849503144374,"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."}}