{"id":"W4405367449","doi":"10.21203/rs.3.rs-5194547/v1","title":"An Exploratory Study on Domain Knowledge Infusion in Deep Learning for Automated Threat Defense","year":2024,"lang":"en","type":"preprint","venue":"Research Square","topic":"Information and Cyber Security","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"National Research Council Canada; Toronto Metropolitan University","funders":"","keywords":"Software deployment; Computer science; Compromise; Context (archaeology); Domain (mathematical analysis); Reinforcement learning; Computer security; Confidentiality; Process (computing); Domain knowledge; Knowledge management; Artificial intelligence; Software engineering; Political science","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","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.005490798,0.0002981562,0.0003383591,0.001420092,0.000388057,0.00088978,0.001418409,0.0003138844,0.00001482426],"category_scores_gemma":[0.0002325406,0.0002716447,0.000123248,0.00107191,0.00005723039,0.0003950585,0.003038546,0.002494133,0.0004685516],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005142636,"about_ca_system_score_gemma":0.0005579551,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005023984,"about_ca_topic_score_gemma":0.0008024207,"domain_scores_codex":[0.9954299,0.001551296,0.0004892481,0.0008405832,0.0009983777,0.0006906233],"domain_scores_gemma":[0.9975345,0.0003981744,0.00008231383,0.001141903,0.0006271384,0.000216027],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003487653,0.004127354,0.003526778,0.003656816,0.0001154825,0.0003738947,0.7681573,0.01188879,0.0001554575,0.1148837,0.003659764,0.08910591],"study_design_scores_gemma":[0.001328648,0.002243889,0.007695919,0.001143032,0.000005917615,0.000003211407,0.02384196,0.9309937,0.0001347389,0.02854445,0.003469004,0.0005954741],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9712747,0.0007265346,0.01334347,0.0003806453,0.0008468618,0.004759655,0.00001717649,0.0020936,0.006557379],"genre_scores_gemma":[0.9977566,0.00003208032,0.0008646296,0.00002512359,0.0001086745,0.001027275,0.00006778113,0.00003371837,0.00008410413],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9191049,"threshold_uncertainty_score":0.9999736,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0682388546154927,"score_gpt":0.4095825879065699,"score_spread":0.3413437332910773,"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."}}