{"id":"W4388483694","doi":"10.1109/ase56229.2023.00100","title":"FLUX: Finding Bugs with LLVM IR Based Unit Test Crossovers","year":2023,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Compiler; Optimizing compiler; Interprocedural optimization; Software bug; Benchmark (surveying); Parallel computing; Fuzz testing; Test suite; Unit testing; Operating system; Programming language; Test case; Software; Loop optimization","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":[],"consensus_categories":[],"category_scores_codex":[0.0003292942,0.0001374939,0.0001159854,0.0002056821,0.0002099192,0.0002634061,0.0006639002,0.00004936737,0.00003335605],"category_scores_gemma":[0.0004572818,0.0001077281,0.00003365879,0.001406966,0.00005471207,0.000227679,0.0001725382,0.0001174906,0.0002381755],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000027799,"about_ca_system_score_gemma":0.0001167675,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001231803,"about_ca_topic_score_gemma":0.000008858762,"domain_scores_codex":[0.9988821,0.00002040282,0.0001237236,0.0003480206,0.0002774291,0.0003483077],"domain_scores_gemma":[0.9981397,0.001064281,0.0000496201,0.0005840957,0.00007324039,0.00008900159],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001708693,0.0001735567,0.3870429,0.00008215164,0.00002889478,0.0004424934,0.00098423,0.000958166,0.001253953,0.01171183,0.5700868,0.02721795],"study_design_scores_gemma":[0.001262373,0.00082904,0.07961266,0.0003585311,0.00001540082,0.00006866902,0.00004163379,0.8677347,0.01329545,0.02242676,0.01320047,0.00115427],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04942098,0.000006580848,0.8568181,0.001640484,0.0001730817,0.0001924479,0.000004551624,0.07696924,0.01477455],"genre_scores_gemma":[0.6878155,5.488918e-7,0.3076593,0.0008154269,0.00002913442,0.00001994249,0.000006856869,0.00001772376,0.003635543],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8667766,"threshold_uncertainty_score":0.4393024,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03891028125000218,"score_gpt":0.2816798097782174,"score_spread":0.2427695285282153,"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."}}