Impact of Sampling Strategies on F1-Score Stability in Code Vulnerability Detection

Abstract

Abstract: This report synthesises findings from 16 peer-reviewed papers addressing the following research question: What is the impact of different sampling strategies (e.g., stratified, random) on the stability of F1-scores for Llama3, Codestral, and Deepseek R1 when evaluated on code vulnerability detection. Large language models (LLMs) are increasingly used in software development, but their level of software security expertise remains unclear. This work systematically evaluates the security comprehension of five leading LLMs: GPT-4o-Mini, GPT-5-Mini, Gemini-2.5-Flash, Llama-3.1. 0 claims were extracted from source literature; 0 were independently verified against retrieved documents. An automated multi-reviewer quality assessment produced a score of 5.0/10. This report is a machine-generated literature synthesis and does not constitute original research.

Research Question

What is the impact of different sampling strategies (e.g., stratified, random) on the stability of F1-scores for Llama3, Codestral, and Deepseek R1 when evaluated on code vulnerability detection benchmarks with varying contamination rates?

Verification Level

Descriptive public verification status only; aggregate claim counts are public, but individual claim records are not exposed here.

Quality Tier

Descriptive public triage only; this tier does not alter current publication or DOI behavior.

Quality Dimensions

Automated triage signals derived from public fields; not human peer review or independent validation.

Correction Record

Public corrections are additive records. Current status does not claim the synthesis is error-free.

Provenance