{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007439189,0.0002509254,0.0002249016,0.0001989106,0.000177582,0.0008854218,0.001792883,0.00008842062,0.00006619091],"category_scores_gemma":[0.0002398598,0.0001879014,0.00009254986,0.0005092248,0.0002241581,0.0005783322,0.0007230609,0.0004411521,0.00006455639],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006016555,"about_ca_system_score_gemma":0.000111206,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006027815,"about_ca_topic_score_gemma":0.000005262107,"domain_scores_codex":[0.9979064,0.00001172055,0.0005108686,0.0006096595,0.000625845,0.0003355131],"domain_scores_gemma":[0.9989763,0.0001573746,0.0001932154,0.000319325,0.0002579773,0.00009582549],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00002367327,0.00008103678,0.0002334349,0.0001235422,0.000026972,0.000003379034,0.001745953,0.0001445842,0.01609648,0.8221167,0.0008960785,0.1585082],"study_design_scores_gemma":[0.0000359361,0.0005660709,0.0006262763,0.001531995,0.00003338764,0.00001357159,0.0004363874,0.3179118,0.6049635,0.06971022,0.00365968,0.000511221],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3435065,0.0006248527,0.4478736,0.03831468,0.002664153,0.003396624,0.00002542418,0.003970628,0.1596236],"genre_scores_gemma":[0.9931769,0.00005881974,0.006080325,0.0002076549,0.00004327636,0.00004584512,0.000001171584,0.00001605837,0.0003699423],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7524064,"threshold_uncertainty_score":0.8538142,"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."}}