{"id":"W4389209036","doi":"10.1145/3611643.3616332","title":"A Generative and Mutational Approach for Synthesizing Bug-Exposing Test Cases to Guide Compiler Fuzzing","year":2023,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"National Natural Science Foundation of China; China Postdoctoral Science Foundation; Tencent","keywords":"Fuzz testing; Computer science; Compiler; Programming language; Compiler correctness; Interprocedural optimization; Optimizing compiler; Code coverage; Compiler construction; Software bug; Toolchain; Test case; Key (lock); Software engineering; Operating system; Loop optimization; Software; Machine learning","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":[0.003942962,0.001895428,0.0007458256,0.002997186,0.0005362889,0.00122827,0.003095113,0.001752559,0.003094225],"category_scores_gemma":[0.02606197,0.0009432844,0.00162623,0.0010414,0.002453688,0.002041166,0.002033066,0.002180691,0.001264282],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001185545,"about_ca_system_score_gemma":0.002245649,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00283026,"about_ca_topic_score_gemma":0.006566877,"domain_scores_codex":[0.9962009,0.001367538,0.0002287509,0.0008316431,0.001122258,0.0002490325],"domain_scores_gemma":[0.9802244,0.01288723,0.001237695,0.003877578,0.00151245,0.0002605837],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004789769,0.0009986525,0.0309962,0.00107732,0.000383096,0.001324174,0.001260698,0.3048037,0.07629439,0.02816959,0.0147316,0.5394816],"study_design_scores_gemma":[0.00009687773,0.0003445611,0.002044015,0.0001431144,0.0001306891,0.0005432387,0.0001208728,0.9274818,0.03840005,0.02337782,0.007255272,0.00006171298],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06518528,0.0005704303,0.9011923,0.0007232683,0.0001000633,0.0005450084,0.0005549614,0.0275616,0.003567048],"genre_scores_gemma":[0.4004613,0.000272682,0.591182,0.000958314,0.00004970262,0.0005793674,0.00170916,0.002321166,0.002466378],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003942962,"threshold_uncertainty_score":0.02085263,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06749669479941017,"score_gpt":0.3200962174909647,"score_spread":0.2525995226915546,"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."}}