{"id":"W4392405447","doi":"10.1109/tifs.2024.3372809","title":"(Security) Assertions by Large Language Models","year":2024,"lang":"en","type":"article","venue":"IEEE Transactions on Information Forensics and Security","topic":"Topic Modeling","field":"Computer Science","cited_by":70,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"Office of Naval Research; Intel Corporation","keywords":"Computer science; Programming language; Natural language processing","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":[0.0001937965,0.0001317075,0.0001076588,0.0001854043,0.0002229471,0.0004437783,0.0001780444,0.00009392395,0.00001585394],"category_scores_gemma":[0.000002299956,0.0001257799,0.00007245709,0.0002969732,0.00002404049,0.003000497,0.000005134692,0.0002847406,0.00004144886],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003919043,"about_ca_system_score_gemma":0.0000419612,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000488007,"about_ca_topic_score_gemma":0.000035697,"domain_scores_codex":[0.9990846,0.00002057316,0.0002725735,0.000178951,0.0002335585,0.0002097319],"domain_scores_gemma":[0.9994815,0.00004399094,0.00003371478,0.0002820494,0.00006208872,0.00009666773],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000008253947,0.00008889252,0.000001780331,0.0001790495,0.00006453834,0.000005586597,0.0336199,0.009395935,0.00007009573,0.852227,0.004026417,0.1003126],"study_design_scores_gemma":[0.0001694343,0.00002849417,9.973223e-7,0.00002874996,0.000009580811,0.00001122198,0.0002756798,0.9509498,0.001171139,0.03728739,0.009920687,0.0001468504],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01127451,0.0001578639,0.9842083,0.0005930601,0.0006353143,0.0001419965,0.000141068,0.000348255,0.002499663],"genre_scores_gemma":[0.9972771,0.00009701018,0.00206546,0.0004282594,0.0000187765,0.00002118187,0.00001804121,0.000005782943,0.00006841614],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9860026,"threshold_uncertainty_score":0.5129155,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.00911134536940814,"score_gpt":0.2310153578091204,"score_spread":0.2219040124397123,"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."}}