{"id":"W2050254119","doi":"10.1109/icstw.2013.49","title":"On Adequacy of Assertions in Automated Test Suites: An Empirical Investigation","year":2013,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"Natural Sciences and Engineering Research Council of Canada; Türkiye Bilimsel ve Teknolojik Araştırma Kurumu","keywords":"Computer science; Oracle; Assertion; Test script; Test (biology); Context (archaeology); Programming language; Unit testing; Test case; Test suite; Source code; Code coverage; Class (philosophy); Empirical research; Keyword-driven testing; Test Management Approach; Test data; Artificial intelligence; Software; Machine learning; Statistics; Mathematics; Software development","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002094829,0.0000802255,0.0001016617,0.000198309,0.00003286532,0.00006788106,0.0003739645,0.00005775764,0.0000183575],"category_scores_gemma":[0.002156014,0.00006699626,0.00001854449,0.0005852335,0.00003681075,0.0004722479,0.00005757682,0.00008706601,0.00004451933],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000279653,"about_ca_system_score_gemma":0.00005836429,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006436924,"about_ca_topic_score_gemma":0.00002388578,"domain_scores_codex":[0.9992007,0.00006280035,0.0002261546,0.0002145201,0.0001539169,0.0001419346],"domain_scores_gemma":[0.9979374,0.001423274,0.00005950149,0.0004069808,0.00009735679,0.00007545578],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[8.844906e-7,0.0004075333,0.9337842,0.00001319547,0.000002449502,0.000002813339,0.0008531482,0.00007824652,0.003237605,0.007596234,0.04655563,0.007468079],"study_design_scores_gemma":[0.00008281386,0.0002386189,0.4967163,0.00004589273,6.817373e-7,0.000002604034,0.000003699981,0.433683,0.0036704,0.0654619,0.000005296802,0.00008880973],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9489598,0.000003478615,0.03213484,0.001160005,0.00003413889,0.0001731857,5.254011e-7,0.01692048,0.000613585],"genre_scores_gemma":[0.8208869,2.318719e-7,0.1785213,0.0005239763,0.000005211756,0.00002640977,0.000002740391,0.000004395716,0.00002887277],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4370679,"threshold_uncertainty_score":0.2732028,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04025660822390811,"score_gpt":0.3265405027542841,"score_spread":0.2862838945303759,"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."}}