@inproceedings{orel-etal-2026-semeval,
title = "{S}em{E}val-2026 Task 13: Detecting Machine-Generated Code with Multiple Programming Languages, Generators, and Application Scenarios",
author = "Orel, Daniil and
Azizov, Dilshod and
Paul, Indraneil and
Wang, Yuxia and
Gurevych, Iryna and
Nakov, Preslav",
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-1.445/",
pages = "3640--3658",
ISBN = "979-8-89176-414-9",
abstract = "We present the results and the main findings of SemEval-2026 Task 13: Detecting Machine-Generated Code with Multiple Programming Languages, Generators, and Application Scenarios. Our task featured three subtasks. Subtask A is a binary classification taskthat determines whether a given code snippet is written by a human or generated by a machine. This subtask focuses on the development of robust methods for AI-generated code identification, since the training and the test data splits have code in different languages and cover diverse usage domains. Subtask B focuses on defining synthetic code smells and requires participants to identify the provenance of the generator family of the model that generated the given code snippet. Subtask C aims at more fine-grained attribution of the written code: whether it was fully AI-generated, fully human-written, produced in human-AI collaboration (hybrid) or by a model tuned or prompted to give human-like code. The task attracted a large number of team members: subtask A (81), subtask B (34), and subtask C (32). In this study, we present the task, analyze the results and discuss the submissions of the system and the methods they used."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="orel-etal-2026-semeval">
<titleInfo>
<title>SemEval-2026 Task 13: Detecting Machine-Generated Code with Multiple Programming Languages, Generators, and Application Scenarios</title>
</titleInfo>
<name type="personal">
<namePart type="given">Daniil</namePart>
<namePart type="family">Orel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dilshod</namePart>
<namePart type="family">Azizov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Indraneil</namePart>
<namePart type="family">Paul</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuxia</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Iryna</namePart>
<namePart type="family">Gurevych</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Preslav</namePart>
<namePart type="family">Nakov</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>We present the results and the main findings of SemEval-2026 Task 13: Detecting Machine-Generated Code with Multiple Programming Languages, Generators, and Application Scenarios. Our task featured three subtasks. Subtask A is a binary classification taskthat determines whether a given code snippet is written by a human or generated by a machine. This subtask focuses on the development of robust methods for AI-generated code identification, since the training and the test data splits have code in different languages and cover diverse usage domains. Subtask B focuses on defining synthetic code smells and requires participants to identify the provenance of the generator family of the model that generated the given code snippet. Subtask C aims at more fine-grained attribution of the written code: whether it was fully AI-generated, fully human-written, produced in human-AI collaboration (hybrid) or by a model tuned or prompted to give human-like code. The task attracted a large number of team members: subtask A (81), subtask B (34), and subtask C (32). In this study, we present the task, analyze the results and discuss the submissions of the system and the methods they used.</abstract>
<identifier type="citekey">orel-etal-2026-semeval</identifier>
<location>
<url>https://aclanthology.org/2026.semeval-1.445/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>3640</start>
<end>3658</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T SemEval-2026 Task 13: Detecting Machine-Generated Code with Multiple Programming Languages, Generators, and Application Scenarios
%A Orel, Daniil
%A Azizov, Dilshod
%A Paul, Indraneil
%A Wang, Yuxia
%A Gurevych, Iryna
%A Nakov, Preslav
%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 orel-etal-2026-semeval
%X We present the results and the main findings of SemEval-2026 Task 13: Detecting Machine-Generated Code with Multiple Programming Languages, Generators, and Application Scenarios. Our task featured three subtasks. Subtask A is a binary classification taskthat determines whether a given code snippet is written by a human or generated by a machine. This subtask focuses on the development of robust methods for AI-generated code identification, since the training and the test data splits have code in different languages and cover diverse usage domains. Subtask B focuses on defining synthetic code smells and requires participants to identify the provenance of the generator family of the model that generated the given code snippet. Subtask C aims at more fine-grained attribution of the written code: whether it was fully AI-generated, fully human-written, produced in human-AI collaboration (hybrid) or by a model tuned or prompted to give human-like code. The task attracted a large number of team members: subtask A (81), subtask B (34), and subtask C (32). In this study, we present the task, analyze the results and discuss the submissions of the system and the methods they used.
%U https://aclanthology.org/2026.semeval-1.445/
%P 3640-3658
Markdown (Informal)
[SemEval-2026 Task 13: Detecting Machine-Generated Code with Multiple Programming Languages, Generators, and Application Scenarios](https://aclanthology.org/2026.semeval-1.445/) (Orel et al., SemEval 2026)
ACL
- Daniil Orel, Dilshod Azizov, Indraneil Paul, Yuxia Wang, Iryna Gurevych, and Preslav Nakov. 2026. SemEval-2026 Task 13: Detecting Machine-Generated Code with Multiple Programming Languages, Generators, and Application Scenarios. In Proceedings of the 20th International Workshop on Semantic Evaluation (2026), pages 3640–3658, San Diego, California, USA. Association for Computational Linguistics.