Procedural Pretraining Scale Effects on CodeT5 Robustness Under Adversarial Attacks

This report synthesises findings from 10 peer-reviewed papers addressing the following research question: How does the scaling of procedural pretraining data size (e.g., 10M vs. 1B tokens) impact CodeT5's robustness on MBPP under adversarial attacks compared to web-scale pretraining. 6 claims were extracted from source literature; 6 were independently verified against retrieved documents. An automated multi-reviewer quality assessment produced a score of 8.3/10. This report is a machine-generated literature synthesis and does not constitute original research.

Research goal: How does the scaling of procedural pretraining data size (e.g., 10M vs. 1B tokens) impact CodeT5's robustness on MBPP under adversarial attacks compared to web-scale pretraining?

Autonomous literature synthesis. Automated review score: 8.3/10. Full text and citation available at Assignee Research.