{"id":"W4395097921","doi":"10.1007/978-3-031-57537-2_15","title":"Enhancing Code Security Through Open-Source Large Language Models: A Comparative Study","year":2024,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Software Engineering Research","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Computer science; Strengths and weaknesses; Code (set theory); Vulnerability (computing); Code review; Source code; Static program analysis; Computer security; Data science; Software engineering; Programming language; Software; Software development","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":[0.007424914,0.0003888291,0.0003527603,0.001440136,0.0006384776,0.003292751,0.001216294,0.0009181332,0.003717754],"category_scores_gemma":[0.04571759,0.0002499121,0.0004666518,0.001374032,0.002088848,0.007731001,0.002323055,0.001524756,0.0006846259],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001932108,"about_ca_system_score_gemma":0.001712007,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001969281,"about_ca_topic_score_gemma":0.002132062,"domain_scores_codex":[0.9934604,0.003503602,0.0002402855,0.0003290696,0.002204807,0.0002617529],"domain_scores_gemma":[0.9284005,0.05523314,0.004353084,0.005900087,0.005323053,0.0007900597],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.008548188,0.005580978,0.05218152,0.0025042,0.0003696296,0.0006867093,0.03061738,0.02685591,0.03722503,0.09169578,0.006148459,0.7375862],"study_design_scores_gemma":[0.001491045,0.02356984,0.1653396,0.003142987,0.002837335,0.004417739,0.07253101,0.3206487,0.1330003,0.1473209,0.1250582,0.0006423404],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9520855,0.001897654,0.02012854,0.0009789994,0.00003375504,0.0001074326,0.0001124345,0.0003975248,0.02425812],"genre_scores_gemma":[0.9884245,0.0008001502,0.007948113,0.00007997072,0.000009683931,0.00004268645,0.0001352625,0.0001629641,0.002396668],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.007424914,"threshold_uncertainty_score":0.03926718,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03903566815580141,"score_gpt":0.3290575166046351,"score_spread":0.2900218484488337,"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."}}