{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.001610108,0.0004225555,0.0004120478,0.0002735122,0.001967338,0.0001882004,0.001497576,0.0001019198,0.0001144537],"category_scores_gemma":[0.00008058149,0.0004222605,0.0001952408,0.001303827,0.0001683233,0.0009185631,0.00002358305,0.001870358,0.00001662184],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007705303,"about_ca_system_score_gemma":0.0003925486,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004127409,"about_ca_topic_score_gemma":0.000009094448,"domain_scores_codex":[0.9956437,0.0007969533,0.0005631215,0.001196053,0.001000331,0.0007997762],"domain_scores_gemma":[0.9969301,0.0008947023,0.0002367756,0.001514603,0.0001715727,0.0002522216],"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":[0.00007832229,0.0002846773,0.0006411587,0.00002761043,0.00002569453,0.00004645906,0.0008428324,0.9839029,0.0005536599,0.0005500037,0.0001155549,0.01293107],"study_design_scores_gemma":[0.0009593935,0.0004866467,0.0006136393,0.00001945695,0.00003216929,0.0001900793,0.0001199038,0.9916206,0.002263742,0.002707066,0.0004635756,0.0005237341],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1078804,0.000008586763,0.8849711,0.0008851202,0.0005471124,0.000551448,0.00002254208,0.0009266536,0.004207018],"genre_scores_gemma":[0.9129187,0.000001266814,0.08590691,0.0005370004,0.00005585891,0.0002593414,0.000003438424,0.00004422613,0.0002732647],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8050383,"threshold_uncertainty_score":0.9998229,"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."}}