{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000435191,0.0001198369,0.0001326169,0.0001770028,0.0003040036,0.000251037,0.0002414286,0.00003270869,9.710718e-7],"category_scores_gemma":[0.001729883,0.0001076721,0.00003042489,0.0004100605,0.00002678974,0.0001839427,0.0002086495,0.00004596712,0.000005891311],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003366147,"about_ca_system_score_gemma":0.0000470376,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006370652,"about_ca_topic_score_gemma":0.000002960336,"domain_scores_codex":[0.9990116,0.00002179555,0.0001810548,0.0003916287,0.0001496428,0.0002442431],"domain_scores_gemma":[0.996769,0.00279208,0.00004129093,0.000202781,0.000111844,0.00008304209],"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":[0.00002959727,0.000366054,0.0307119,0.0003349194,0.0001201346,0.0002374155,0.01256986,0.008712387,0.02424986,0.079688,0.5266127,0.3163672],"study_design_scores_gemma":[0.0001834758,0.0002056641,0.002632577,0.00009556222,0.000009086784,0.0001927462,0.0001110919,0.9717102,0.01033878,0.01331692,0.000810049,0.0003938654],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00809,0.00002626867,0.9831663,0.0006857348,0.00004746806,0.0002754479,0.00000674673,0.006757366,0.000944713],"genre_scores_gemma":[0.2316761,8.535658e-7,0.7673804,0.0005946787,0.00006158763,0.0001111185,0.000007129775,0.0000107479,0.0001573138],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9629978,"threshold_uncertainty_score":0.4390741,"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."}}