{"id":"W2766877844","doi":"10.1007/s11334-017-0306-1","title":"Predicting different levels of the unit testing effort of classes using source code metrics: a multiple case study on open-source software","year":2017,"lang":"en","type":"article","venue":"Innovations in Systems and Software Engineering","topic":"Software Engineering Research","field":"Computer Science","cited_by":23,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université Laval; Université du Québec à Trois-Rivières","funders":"","keywords":"Unit testing; Computer science; Software quality assurance; Software engineering; Software reliability testing; Regression testing; Software metric; Software quality; Non-regression testing; Metric (unit); Quality assurance; Manual testing; Quality (philosophy); Source code; Keyword-driven testing; Software construction; Reliability engineering; Software system; Software; Software development; Programming language; Engineering","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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.001139952,0.0002501124,0.0004565342,0.0006337449,0.0004598715,0.000417584,0.001518718,0.00009525973,4.239501e-7],"category_scores_gemma":[0.01633386,0.0002080211,0.00003881869,0.001560573,0.0000589429,0.000458823,0.001486778,0.0004191188,1.430405e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001164666,"about_ca_system_score_gemma":0.00009669037,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002035565,"about_ca_topic_score_gemma":0.00006136412,"domain_scores_codex":[0.9979221,0.00006031379,0.0007627505,0.0004084747,0.0005079615,0.0003383878],"domain_scores_gemma":[0.9945617,0.003210467,0.000432901,0.001299632,0.0004353391,0.00005998715],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.000001477119,0.00008188694,0.8292896,0.0001897365,0.00003759179,0.00003481621,0.0009499528,0.1670355,0.0002717305,0.00007473391,0.000001230544,0.002031703],"study_design_scores_gemma":[0.0007418396,0.0001087065,0.6395231,0.0009478174,0.00001144607,0.0002199734,0.0006143331,0.3571128,0.0004561029,0.000003780526,0.0000288549,0.0002312473],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6022623,0.00004602561,0.3967486,0.000004469123,0.0002695064,0.0005402532,0.00001514163,0.0001122286,0.000001481148],"genre_scores_gemma":[0.9779847,4.865711e-7,0.02184428,0.000003003012,0.0000426989,0.00006343534,5.522991e-7,0.00004133978,0.00001954202],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3757223,"threshold_uncertainty_score":0.991952,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1190979416749238,"score_gpt":0.329284302935347,"score_spread":0.2101863612604232,"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."}}