Contrastive Loss Margin Tuning and Adversarial Training in CodeT5 Robustness on MBXP Python

Abstract

Abstract: This report synthesises findings from 12 peer-reviewed papers addressing the following research question: How does the combination of contrastive loss margin tuning and adversarial training impact the trade-off between clean accuracy and adversarial robustness in CodeT5 for the MBXP Python subset, as. 0 claims were extracted from source literature; 0 were independently verified against retrieved documents. An automated multi-reviewer quality assessment produced a score of 1.8/10. This report is a machine-generated literature synthesis and does not constitute original research.

Research Question

How does the combination of contrastive loss margin tuning and adversarial training impact the trade-off between clean accuracy and adversarial robustness in CodeT5 for the MBXP Python subset, as measured by accuracy differentials between FGSM and PGD attacks?

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