Index  |  Benchmarks  |  Mathematics  |  Graph  |  About
SRCH:F517E814

Subword Sampling and Gaussian Noise Augmentations in CodeT5 Consistency Regularization for MBPP

Submitted: 7 June 2026
Review score: 2.50/10
Verification: L1, Literature synthesis
Quality tier: Quarantine candidate

Abstract

Abstract: This report synthesises findings from 8 peer-reviewed papers addressing the following research question: How does the inclusion of subword sampling and Gaussian noise augmentations in consistency regularization affect the performance of CodeT5 models on the MBPP benchmark compared to other adversarial. 0 claims were extracted from source literature; 0 were independently verified against retrieved documents. An automated multi-reviewer quality assessment produced a score of 2.5/10. This report is a machine-generated literature synthesis and does not constitute original research.

Research Question

How does the inclusion of subword sampling and Gaussian noise augmentations in consistency regularization affect the performance of CodeT5 models on the MBPP benchmark compared to other adversarial perturbation techniques?

Verification Level

Paper levelL1, Literature synthesis
Source-grounded claims0
Claim record sourcenot publicly specified

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

Quality Tier

TierQuarantine candidate
BasisReview score is below 5.0; source-level inspection is required before relying on the synthesis.

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

Quality Dimensions

Evidence strength LOW
Uncertainty disclosure MEDIUM
Reproducibility status MEDIUM

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

Correction Record

StatusCURRENT
Correction count0
Manifest contractpaper-manifest-v1.1
Correction contractcorrection-record-v1

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

Provenance

PublisherAssignee Research
Public provenanceL2, Public artifact record
Report artifactAvailable
External recordNot registered
Claim lineage0 aggregate source-grounded claims
Review methodAutomated multi-reviewer assessment
Quality guideHow to read scores, claims, manifests, and evidence links
Provenance contractsource-provenance-v1
NoteMachine-generated synthesis of existing literature. Not primary research.