{"id":"W2164694023","doi":"10.1145/2492248.2492261","title":"On the relationship between use cases and test suites size","year":2013,"lang":"en","type":"article","venue":"ACM SIGSOFT Software Engineering Notes","topic":"Software Engineering Research","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université du Québec à Trois-Rivières","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Test Management Approach; Test (biology); Software quality; Test case; Regression testing; Software; Software engineering; Perspective (graphical); Software metric; Manual testing; Reliability engineering; Software system; Software development; Software construction; Programming language; Engineering; Machine learning; Artificial intelligence","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[{"model":"gemma","categories":["metaresearch"],"domain":"methods","study_design":"observational","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"high","status":"direct model label, unvalidated"},{"model":"gpt","categories":[],"domain":null,"study_design":"observational","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"high","status":"direct model label, unvalidated"}],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003620797,0.0003267204,0.0002339385,0.0001862037,0.0002347665,0.0006818112,0.001284471,0.0001339888,0.00003732026],"category_scores_gemma":[0.9760273,0.0002565866,0.00006851998,0.0006633329,0.00006749975,0.0008665721,0.0006090963,0.0005509686,0.0001995341],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006520736,"about_ca_system_score_gemma":0.00004052323,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001120688,"about_ca_topic_score_gemma":0.000001321954,"domain_scores_codex":[0.9981534,0.00004434101,0.0002744838,0.0004998423,0.0004565145,0.0005713814],"domain_scores_gemma":[0.005124339,0.9930493,0.00005401476,0.001415775,0.000129528,0.000227066],"domain_codex":null,"domain_gemma":"methods","domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[5.366665e-7,0.00001422684,0.995297,0.00003272111,0.00001322023,0.00001249304,0.000119718,0.00006196729,0.000111038,0.00276365,0.0007512487,0.0008221575],"study_design_scores_gemma":[0.0001214597,0.00009520203,0.9983797,0.00009823639,0.000006699563,0.00002612434,0.000002930461,0.00006368813,0.000581282,0.0001620603,0.0001528786,0.0003097575],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9938985,0.0001745959,0.002932714,0.001166994,0.0001283642,0.0003698579,0.00001603812,0.001312752,2.450385e-7],"genre_scores_gemma":[0.9736013,0.000005661272,0.02586291,0.0001373671,0.0001128448,0.0001253799,0.000005253419,0.00005558136,0.00009368152],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9930291,"threshold_uncertainty_score":0.9999886,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05497642424938919,"score_gpt":0.2632104469901711,"score_spread":0.2082340227407819,"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."}}