{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003037178,0.001308363,0.0006795378,0.002499403,0.000601661,0.0009727423,0.001676907,0.001291421,0.002301765],"category_scores_gemma":[0.0161069,0.0006042729,0.001061755,0.0008239111,0.001349275,0.002102048,0.001811505,0.0009961107,0.000540078],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001041131,"about_ca_system_score_gemma":0.001217283,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002881402,"about_ca_topic_score_gemma":0.003813807,"domain_scores_codex":[0.9968082,0.0007358387,0.0002111386,0.0006905016,0.001274139,0.0002801128],"domain_scores_gemma":[0.9926051,0.004058423,0.001081475,0.001233659,0.0007928667,0.0002284149],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.002454805,0.000834477,0.1691991,0.001250933,0.0004638332,0.002897646,0.002127691,0.09450492,0.1307272,0.01619889,0.03004851,0.549292],"study_design_scores_gemma":[0.0004500825,0.001970496,0.02905908,0.0003018848,0.0003333326,0.002470348,0.0005929298,0.76977,0.1560608,0.01947228,0.01931266,0.0002063367],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5505313,0.001468955,0.346379,0.0008404512,0.0001991923,0.000501741,0.001902458,0.09257088,0.005606058],"genre_scores_gemma":[0.7621904,0.0001900803,0.229199,0.0005083396,0.00003870328,0.000300956,0.002705469,0.002790241,0.002076793],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.003037178,"threshold_uncertainty_score":0.01606238,"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."}}