Reference health
Assessing and Improving Syntactic Adversarial Robustness of Pre-Trained Models for Code Translation
17/17 checkable references clean · checked 2026-09-06
Every reference with a DOI in the deposited reference list resolved to a known work in Crossref or DataCite at the dated check, and none carried a retraction, withdrawal, or removal notice.
40 without a DOI — not checked. A reference deposited without a DOI is never matched by title or guessed at; it stays outside the checked set, and this line discloses that.
The 17 checked references that resolve
resolves10.1609/aaai.v34i01.5469
Generating Adversarial Examples for Holding Robustness of Source Code Processing Models
resolves10.1145/3533767.3534390
An extensive study on pre-trained models for program understanding and generation
resolves10.18653/v1/2021.emnlp-main.685
CodeT5: Identifier-aware Unified Pre-trained Encoder-Decoder Models for Code Understanding and Generation
resolves10.1109/ICST49551.2021.00016
A Search-Based Testing Framework for Deep Neural Networks of Source Code Embedding
resolves10.1609/aaai.v37i12.26739
CodeAttack: Code-Based Adversarial Attacks for Pre-trained Programming Language Models
resolves10.1145/3511887
Towards Robustness of Deep Program Processing Models—Detection, Estimation, and Enhancement
resolves10.1109/QRS54544.2021.00090
Generating Adversarial Examples of Source Code Classification Models via Q-Learning-Based Markov Decision Process
resolves10.1145/3197231.3197240
Automatic inference of Java-to-swift translation rules for porting mobile applications
The 40 references without a DOI — listed, not checked
no DOI — not checkedPerfection not required? human-ai partnerships in code translation
no DOI — not checkedref2
no DOI — not checkedUnsupervised translation of programming languages
no DOI — not checkedLeveraging automated unit tests for unsupervised code translation
no DOI — not checkedref5
no DOI — not checkedOn the generalizability of neural program models with respect to semanticpreserving program transformations
no DOI — not checkedHow important are good method names in neural code generation? a model robustness perspective
no DOI — not checkedref13
no DOI — not checkedExpectation vs. experience: Evaluating the usability of code generation tools powered by large language models
no DOI — not checkedref15
no DOI — not checkedref17
no DOI — not checkedCodexglue: A machine learning benchmark dataset for code understanding and generation
no DOI — not checkedref20
no DOI — not checkedCocofuzzing: Testing neural code models with coverage-guided fuzzing
no DOI — not checkedGenerating adversarial source programs using important tokens-based structural transformations
no DOI — not checkedProgramtransformer: A tool for generating semantically equivalent transformed programs
no DOI — not checkedref27
no DOI — not checkedAttention is all you need
no DOI — not checkedEvaluating generated text as text generation
no DOI — not checkedOn the naturalness of software
no DOI — not checkedref35
no DOI — not checkedAdversarial robustness for code
no DOI — not checkedTowards deep learning models resistant to adversarial attacks
no DOI — not checkedref38
no DOI — not checkedBleu: a method for automatic evaluation of machine translation
no DOI — not checkedref40
no DOI — not checkedref41
no DOI — not checkedref42
no DOI — not checkedGraphcodebert: Pre-training code representations with data flow
no DOI — not checkedCodegen: An open large language model for code with multiturn program synthesis
no DOI — not checkedUnified pre-training for program understanding and generation
no DOI — not checkedUnixcoder: Unified cross-modal pre-training for code representation
no DOI — not checkedEmergent abilities of large language models
no DOI — not checkedTraining language models to follow instructions with human feedback
no DOI — not checkedref49
no DOI — not checkedref50
no DOI — not checkedPhrase-based statistical translation of programming languages
no DOI — not checkedMining api mapping for language migration
no DOI — not checkedDobf: A deobfuscation pre-training objective for programming languages
no DOI — not checkedref57
What this badge says. CiteStamped means the CHECKABLE references of this
work were clean at the dated check: each resolved to a known work in a public registry, and none
carried a retraction notice at that time. It says nothing about the quality, findings,
or importance of the work itself, and nothing about references deposited without a DOI.
checked 2026-09-06 — re-checked daily as this page is visited; titles and statuses come from Crossref and DataCite and are not part of the signed record
Embed this badge
Both snippets point at the live badge image and link back to this page. The badge re-renders from the daily check, so an embed never goes stale by more than a day of visits.
<a href="https://citestamp.com/citestamped/10.2139/ssrn.4623115"><img src="https://citestamp.com/citestamped/10.2139/ssrn.4623115/badge.svg" alt="CiteStamped reference-health badge" width="460" height="64"></a>
[](https://citestamp.com/citestamped/10.2139/ssrn.4623115)