{"id":"W96424918","doi":"10.1007/978-3-642-41707-8_8","title":"Predicting the Size of Test Suites from Use Cases: An Empirical Exploration","year":2013,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Software Engineering Research","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université du Québec à Trois-Rivières","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Regression testing; Univariate; Metric (unit); Logistic regression; Software metric; Software quality; Software; Test case; Software regression; Data mining; Reliability engineering; Regression analysis; Multivariate statistics; Machine learning; Software development; Software construction; Programming language","routes":{"ca_aff":true,"ca_fund":true,"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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.008555839,0.001271366,0.0007506275,0.003489755,0.0003358922,0.001682863,0.001947345,0.001344296,0.001442075],"category_scores_gemma":[0.142785,0.0006420966,0.001055513,0.002706492,0.000734868,0.00373649,0.0009098203,0.001887488,0.0006011403],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008577736,"about_ca_system_score_gemma":0.0009601013,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002735696,"about_ca_topic_score_gemma":0.004404268,"domain_scores_codex":[0.9933779,0.003060925,0.0005297509,0.0009741505,0.001825727,0.0002316634],"domain_scores_gemma":[0.5310652,0.4438956,0.009767502,0.009022395,0.005001728,0.001247528],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.001743702,0.002277411,0.5673098,0.000771707,0.0005443766,0.000580295,0.001021147,0.1728894,0.00475225,0.002008941,0.003421423,0.2426797],"study_design_scores_gemma":[0.0001035042,0.001133466,0.1436318,0.0001272344,0.000221571,0.0007032077,0.0005211259,0.8408381,0.004934434,0.006550799,0.001171154,0.0000636747],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9794418,0.0008282032,0.01677813,0.0001836106,0.00001297484,0.00008955604,0.001306055,0.0003332114,0.001026561],"genre_scores_gemma":[0.9837384,0.0002264872,0.01305914,0.0000304101,0.00001547901,0.00006843148,0.002413075,0.00007452306,0.0003739237],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9914442,"threshold_uncertainty_score":0.04524815,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0534479459431185,"score_gpt":0.2939177886312423,"score_spread":0.2404698426881239,"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."}}