{"id":"W4393145551","doi":"10.1609/aaai.v38i21.30455","title":"BertRLFuzzer: A BERT and Reinforcement Learning Based Fuzzer (Student Abstract)","year":2024,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Data Stream Mining Techniques","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Reinforcement learning; Computer science; Fuzz testing; Reinforcement; Artificial intelligence; Programming language; Engineering; Software; Structural engineering","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":[0.001760419,0.001032276,0.0005406206,0.0008292225,0.0003337118,0.0009120826,0.002376296,0.001615787,0.006120617],"category_scores_gemma":[0.006986615,0.0004761,0.0007309915,0.0003035551,0.001075046,0.002004646,0.001337816,0.001572338,0.001164959],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000810263,"about_ca_system_score_gemma":0.0008410977,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003029529,"about_ca_topic_score_gemma":0.003031492,"domain_scores_codex":[0.9991224,0.0002094177,0.00005408334,0.000219128,0.0003117929,0.00008310058],"domain_scores_gemma":[0.9973183,0.001581871,0.0002301274,0.0005287055,0.0002388179,0.0001020352],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001037468,0.0005949894,0.0111586,0.0004774095,0.0002774183,0.0006227799,0.0003667961,0.5196581,0.05233317,0.02433855,0.01213901,0.3769957],"study_design_scores_gemma":[0.00006332764,0.0002440189,0.0006510624,0.00002636983,0.00002683567,0.0001746436,0.00001512941,0.9680684,0.02112717,0.004719995,0.004851817,0.0000311724],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0891881,0.0005197327,0.8493305,0.0006789451,0.0001167154,0.0002873524,0.0004331378,0.05466759,0.004777964],"genre_scores_gemma":[0.6123728,0.0001740828,0.3790496,0.0004787169,0.00002979043,0.000224644,0.0005528276,0.001198067,0.005919532],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006120617,"threshold_uncertainty_score":0.02047551,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05321952071557166,"score_gpt":0.3118040325938566,"score_spread":0.258584511878285,"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."}}