{"id":"W4287117507","doi":"10.1109/tr.2022.3208239","title":"CoCoFuzzing: Testing Neural <u>Co</u>de Models With <u>Co</u>verage-Guided <u>Fuzzing</u>","year":2022,"lang":"en","type":"article","venue":"IEEE Transactions on Reliability","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University; York University","funders":"","keywords":"Generalizability theory; Robustness (evolution); Fuzz testing; Computer science; Artificial intelligence; Source code; Automatic summarization; Artificial neural network; Code (set theory); Machine learning; Natural language processing; Programming language; Mathematics; Software; Statistics","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":[0.002543521,0.001308029,0.0005307209,0.0008831136,0.000377445,0.0008670089,0.002345727,0.00164662,0.002261056],"category_scores_gemma":[0.01612915,0.000392872,0.0008387743,0.0003654459,0.001170227,0.001882163,0.001187136,0.001424645,0.0003421288],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001752232,"about_ca_system_score_gemma":0.001763675,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01467129,"about_ca_topic_score_gemma":0.01720737,"domain_scores_codex":[0.9985052,0.0003265546,0.0001100931,0.0005094467,0.0003603678,0.0001882734],"domain_scores_gemma":[0.9892033,0.007059956,0.0007545269,0.001641973,0.001092607,0.0002477045],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0008028809,0.0003263137,0.02424821,0.0001588362,0.0002052138,0.0002672295,0.0001336701,0.8186872,0.01101669,0.007061705,0.004257129,0.1328349],"study_design_scores_gemma":[0.0000101678,0.00005385996,0.0003820304,0.000005548358,0.0000075962,0.00002152871,0.00001068393,0.9924966,0.005819301,0.001021518,0.0001664289,0.000004775117],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6077134,0.0003997475,0.375789,0.0009149671,0.0001341593,0.0002156527,0.001061256,0.008846575,0.004925246],"genre_scores_gemma":[0.9358642,0.00003957365,0.06143291,0.0003072463,0.00001237469,0.00008871371,0.0009828233,0.0001725373,0.001099669],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01467129,"threshold_uncertainty_score":0.02917182,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04105776073760289,"score_gpt":0.2860585000762557,"score_spread":0.2450007393386528,"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."}}