{"id":"W2740565296","doi":"10.1145/3106237.3106258","title":"QTEP: quality-aware test case prioritization","year":2017,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":73,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Code coverage; Computer science; Source code; Software quality; Leverage (statistics); Test case; Test suite; Code (set theory); Code review; Reliability engineering; Software; Programming language; Software development; Set (abstract data type); Engineering","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":[0.0003701004,0.00008399178,0.00009245145,0.00004195673,0.0006000994,0.0005996401,0.0007711459,0.00004768248,0.000007692422],"category_scores_gemma":[0.001710183,0.00007482505,0.00002943751,0.00005932571,0.00004239948,0.0005019312,0.0003144511,0.00007027887,0.00003741944],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001920774,"about_ca_system_score_gemma":0.00003593013,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008512137,"about_ca_topic_score_gemma":0.00004984654,"domain_scores_codex":[0.9992746,0.00002598515,0.0001471039,0.0002574047,0.0001398924,0.0001550822],"domain_scores_gemma":[0.9980938,0.0003299194,0.0001169232,0.001281339,0.0001143257,0.00006364595],"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":[0.000002329998,0.0002528548,0.2838629,0.00007535436,0.00001297589,0.002715815,0.0007862179,0.00000441615,0.0002143832,0.1013431,0.1051986,0.5055311],"study_design_scores_gemma":[0.001665336,0.000642158,0.18897,0.0003795817,0.00002763736,0.01054286,0.00005413559,0.2621185,0.01266372,0.5090991,0.01128562,0.002551315],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005114618,0.00001302321,0.974626,0.001110133,0.0001762635,0.00008714039,0.000001850884,0.01171677,0.007154176],"genre_scores_gemma":[0.8000531,0.000001731432,0.1990384,0.0002322428,0.00005128327,0.000006811862,8.449812e-7,0.000005312275,0.0006103549],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7949384,"threshold_uncertainty_score":0.5782343,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05778218964391741,"score_gpt":0.3646264952223595,"score_spread":0.3068443055784421,"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."}}