{"id":"W4399909891","doi":"10.1109/icnc59896.2024.10556056","title":"Accelerating Autonomous Cyber Operations: A Symbolic Logic Planner Guided Reinforcement Learning Approach","year":2024,"lang":"en","type":"article","venue":"","topic":"AI-based Problem Solving and Planning","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Defence Research and Development Canada; Queen's University","funders":"","keywords":"Planner; Reinforcement learning; Computer science; Logic programming; Artificial intelligence; Human–computer interaction","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":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0006538176,0.0002074334,0.0001734753,0.0001731182,0.0004567839,0.001373265,0.0005357036,0.00008978548,0.0001615526],"category_scores_gemma":[0.00005870511,0.0001655118,0.00007128821,0.0004379052,0.00001947682,0.0006990677,0.0002352144,0.0003915476,0.0002254519],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008001646,"about_ca_system_score_gemma":0.0001790762,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00019041,"about_ca_topic_score_gemma":0.000003825332,"domain_scores_codex":[0.9983275,0.00009228825,0.000381423,0.0005384377,0.0002560095,0.0004043217],"domain_scores_gemma":[0.9993454,0.0001194531,0.00003362531,0.0003453658,0.00005802961,0.0000981733],"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":[8.289177e-7,0.00001235255,0.00007257974,0.0000419992,0.00002955016,0.00002428671,0.002769372,0.7975724,0.0002626956,0.1879996,0.004746708,0.006467639],"study_design_scores_gemma":[0.0001066074,0.00006293059,0.000017499,0.0000775087,0.000007244152,0.00006417764,0.00008536495,0.9885752,0.0002829226,0.0004074493,0.0100625,0.0002505763],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002405977,0.0005478385,0.8994119,0.0009381668,0.0002679892,0.0002067781,4.659986e-7,0.00122581,0.09499505],"genre_scores_gemma":[0.7843896,0.000009489363,0.1972151,0.0007761969,0.0001583959,0.0000752592,0.00004009554,0.0000184241,0.01731746],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7819836,"threshold_uncertainty_score":0.9996634,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05025189694048924,"score_gpt":0.2804685489694158,"score_spread":0.2302166520289265,"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."}}