{"id":"W2097666838","doi":"10.1109/iri.2009.5211557","title":"Scalability improvement in software evaluation methodologies","year":2009,"lang":"en","type":"article","venue":"","topic":"Software Engineering Research","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"","keywords":"Scalability; Computer science; Software; Dependency (UML); Adaptation (eye); Software engineering; Software metric; Software development; Software quality; Reliability engineering; Engineering; Database; Operating system","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":[0.0829753,0.001884959,0.001554913,0.007591727,0.001400642,0.005196741,0.003146198,0.001802407,0.001461],"category_scores_gemma":[0.1857231,0.001206118,0.001742396,0.004425974,0.001965035,0.008692028,0.004661406,0.003295519,0.0006606244],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.004132908,"about_ca_system_score_gemma":0.004904165,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002243095,"about_ca_topic_score_gemma":0.001928382,"domain_scores_codex":[0.8885416,0.0568005,0.01040096,0.005410455,0.03705332,0.001793151],"domain_scores_gemma":[0.8114328,0.1011714,0.01401691,0.02188498,0.0501033,0.001390744],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001848198,0.0004109728,0.01032425,0.00302164,0.0004561997,0.0003482362,0.002176452,0.04777067,0.0117761,0.09602508,0.006048078,0.8214576],"study_design_scores_gemma":[0.0003465131,0.001457489,0.01665398,0.004925646,0.0008713731,0.001923904,0.002766074,0.5379247,0.03013743,0.2851562,0.1173895,0.0004472148],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02859711,0.006726746,0.9434829,0.0030116,0.0002081433,0.001072424,0.00009925385,0.001765831,0.01503609],"genre_scores_gemma":[0.2314546,0.002448459,0.7621965,0.0005079684,0.0002268623,0.0008830067,0.0002462525,0.0003604069,0.001675913],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.0829753,"threshold_uncertainty_score":0.4388205,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08660750563061385,"score_gpt":0.3801430347165661,"score_spread":0.2935355290859523,"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."}}