@inproceedings{creo-etal-2026-coodetect,
title = "{COOD}etect at {S}em{E}val-2026 Task 13: Unsupervised Latent Domain Adaptation for Out-of-Distribution {AI} Code Detection",
author = "Creo, Aldan and
Nair, Atharv and
Ravikumar, Mohana and
Menon, Vaishak and
Wisznewer, Dario and
Jain, Vaibhav",
editor = "Kochmar, Ekaterina and
Ghosh, Debanjan and
North, Kai and
Komachi, Mamoru",
booktitle = "Proceedings of the 20th {I}nternational {W}orkshop on {S}emantic {E}valuation (2026)",
month = jul,
year = "2026",
address = "San Diego, California, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.semeval-1.187/",
pages = "1443--1450",
ISBN = "979-8-89176-414-9",
abstract = "The widespread use of AI-generated code raises questions about software maintenance and academic integrity. However, tools to detect it are still in their infancy. In this article, we explore the issue of out-of-distribution (OOD) detection; while embedder models like CodeBERT can easily achieve high accuracies in the context of their training data, they are unable to properly generalize to unseen contexts or programming languages. We argue that this is caused by an overfitting of such models to the training distribution, e.g. memorizing a language{'}s ``AI syntax'' instead of the true generative artifacts, and develop a approach that is able to naturally generalize to completely unseen languages and domains. Our system is also considerably more interpretable than the deep neural alternatives. In particular, we propose three orthogonal views (lexical, structural, and symbolic) to capture the AI-generated code{'}s indicators. To deal with OOD shift, we normalize the scores per language with Z-scoring and a Gaussian Mixture Model to remove the language bias automatically. We test our approach on the SemEval-2026 Task 13 dataset, where our experiments reached a macro F1 of 0.602 compared to the task baseline of 0.305, demonstrating the generalization capabilities of our system. We make our source code and data available at https://github.com/ACMCMC/COODetect."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="creo-etal-2026-coodetect">
<titleInfo>
<title>COODetect at SemEval-2026 Task 13: Unsupervised Latent Domain Adaptation for Out-of-Distribution AI Code Detection</title>
</titleInfo>
<name type="personal">
<namePart type="given">Aldan</namePart>
<namePart type="family">Creo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Atharv</namePart>
<namePart type="family">Nair</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohana</namePart>
<namePart type="family">Ravikumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vaishak</namePart>
<namePart type="family">Menon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dario</namePart>
<namePart type="family">Wisznewer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vaibhav</namePart>
<namePart type="family">Jain</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 20th International Workshop on Semantic Evaluation (2026)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Kochmar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Debanjan</namePart>
<namePart type="family">Ghosh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kai</namePart>
<namePart type="family">North</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mamoru</namePart>
<namePart type="family">Komachi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">San Diego, California, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-414-9</identifier>
</relatedItem>
<abstract>The widespread use of AI-generated code raises questions about software maintenance and academic integrity. However, tools to detect it are still in their infancy. In this article, we explore the issue of out-of-distribution (OOD) detection; while embedder models like CodeBERT can easily achieve high accuracies in the context of their training data, they are unable to properly generalize to unseen contexts or programming languages. We argue that this is caused by an overfitting of such models to the training distribution, e.g. memorizing a language’s “AI syntax” instead of the true generative artifacts, and develop a approach that is able to naturally generalize to completely unseen languages and domains. Our system is also considerably more interpretable than the deep neural alternatives. In particular, we propose three orthogonal views (lexical, structural, and symbolic) to capture the AI-generated code’s indicators. To deal with OOD shift, we normalize the scores per language with Z-scoring and a Gaussian Mixture Model to remove the language bias automatically. We test our approach on the SemEval-2026 Task 13 dataset, where our experiments reached a macro F1 of 0.602 compared to the task baseline of 0.305, demonstrating the generalization capabilities of our system. We make our source code and data available at https://github.com/ACMCMC/COODetect.</abstract>
<identifier type="citekey">creo-etal-2026-coodetect</identifier>
<location>
<url>https://aclanthology.org/2026.semeval-1.187/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>1443</start>
<end>1450</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T COODetect at SemEval-2026 Task 13: Unsupervised Latent Domain Adaptation for Out-of-Distribution AI Code Detection
%A Creo, Aldan
%A Nair, Atharv
%A Ravikumar, Mohana
%A Menon, Vaishak
%A Wisznewer, Dario
%A Jain, Vaibhav
%Y Kochmar, Ekaterina
%Y Ghosh, Debanjan
%Y North, Kai
%Y Komachi, Mamoru
%S Proceedings of the 20th International Workshop on Semantic Evaluation (2026)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, USA
%@ 979-8-89176-414-9
%F creo-etal-2026-coodetect
%X The widespread use of AI-generated code raises questions about software maintenance and academic integrity. However, tools to detect it are still in their infancy. In this article, we explore the issue of out-of-distribution (OOD) detection; while embedder models like CodeBERT can easily achieve high accuracies in the context of their training data, they are unable to properly generalize to unseen contexts or programming languages. We argue that this is caused by an overfitting of such models to the training distribution, e.g. memorizing a language’s “AI syntax” instead of the true generative artifacts, and develop a approach that is able to naturally generalize to completely unseen languages and domains. Our system is also considerably more interpretable than the deep neural alternatives. In particular, we propose three orthogonal views (lexical, structural, and symbolic) to capture the AI-generated code’s indicators. To deal with OOD shift, we normalize the scores per language with Z-scoring and a Gaussian Mixture Model to remove the language bias automatically. We test our approach on the SemEval-2026 Task 13 dataset, where our experiments reached a macro F1 of 0.602 compared to the task baseline of 0.305, demonstrating the generalization capabilities of our system. We make our source code and data available at https://github.com/ACMCMC/COODetect.
%U https://aclanthology.org/2026.semeval-1.187/
%P 1443-1450
Markdown (Informal)
[COODetect at SemEval-2026 Task 13: Unsupervised Latent Domain Adaptation for Out-of-Distribution AI Code Detection](https://aclanthology.org/2026.semeval-1.187/) (Creo et al., SemEval 2026)
ACL