@inproceedings{gainulla-shamsadinov-2026-youngdsmlkz,
title = "{Y}oung{DSMLKZ} at {S}em{E}val-2026 Task 13: {MIL}-{U}ni{X}coder with Meta-Stacking and Handcrafted Features for {AI}-Generated Code Detection",
author = "Gainulla, Yeraly and
Shamsadinov, Agzam",
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-1.137/",
pages = "994--999",
ISBN = "979-8-89176-414-9",
abstract = "We propose and validate a multi-view ensemble framework for 4-class AI-generated code detection (Human, AI, Hybrid, Adversarial) in realistic long-form repositories. Our system, Team YoungDSMLKZ, ranked 1st out of 50+ teams in SemEval-2026 Task 13 Subtask C with a macro F1 of 0.7855 (+5.2 over runner-up). The framework combines: (i) a Dynamic Multiple Instance Learning (MIL) pipeline over UniXcoder chunks for O(N)-scalable long-context detection, (ii) transformer-based meta-stacking (UniXcoder and ModernBERT), and (iii) an XGBoost classifier on 200+ handcrafted stylometric features. Evidence localization analysis shows that 62.4{\%} of decisive AI-detection signals reside beyond the standard 512-token window, validating the MIL design."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="gainulla-shamsadinov-2026-youngdsmlkz">
<titleInfo>
<title>YoungDSMLKZ at SemEval-2026 Task 13: MIL-UniXcoder with Meta-Stacking and Handcrafted Features for AI-Generated Code Detection</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yeraly</namePart>
<namePart type="family">Gainulla</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Agzam</namePart>
<namePart type="family">Shamsadinov</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 propose and validate a multi-view ensemble framework for 4-class AI-generated code detection (Human, AI, Hybrid, Adversarial) in realistic long-form repositories. Our system, Team YoungDSMLKZ, ranked 1st out of 50+ teams in SemEval-2026 Task 13 Subtask C with a macro F1 of 0.7855 (+5.2 over runner-up). The framework combines: (i) a Dynamic Multiple Instance Learning (MIL) pipeline over UniXcoder chunks for O(N)-scalable long-context detection, (ii) transformer-based meta-stacking (UniXcoder and ModernBERT), and (iii) an XGBoost classifier on 200+ handcrafted stylometric features. Evidence localization analysis shows that 62.4% of decisive AI-detection signals reside beyond the standard 512-token window, validating the MIL design.</abstract>
<identifier type="citekey">gainulla-shamsadinov-2026-youngdsmlkz</identifier>
<location>
<url>https://aclanthology.org/2026.semeval-1.137/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>994</start>
<end>999</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T YoungDSMLKZ at SemEval-2026 Task 13: MIL-UniXcoder with Meta-Stacking and Handcrafted Features for AI-Generated Code Detection
%A Gainulla, Yeraly
%A Shamsadinov, Agzam
%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 gainulla-shamsadinov-2026-youngdsmlkz
%X We propose and validate a multi-view ensemble framework for 4-class AI-generated code detection (Human, AI, Hybrid, Adversarial) in realistic long-form repositories. Our system, Team YoungDSMLKZ, ranked 1st out of 50+ teams in SemEval-2026 Task 13 Subtask C with a macro F1 of 0.7855 (+5.2 over runner-up). The framework combines: (i) a Dynamic Multiple Instance Learning (MIL) pipeline over UniXcoder chunks for O(N)-scalable long-context detection, (ii) transformer-based meta-stacking (UniXcoder and ModernBERT), and (iii) an XGBoost classifier on 200+ handcrafted stylometric features. Evidence localization analysis shows that 62.4% of decisive AI-detection signals reside beyond the standard 512-token window, validating the MIL design.
%U https://aclanthology.org/2026.semeval-1.137/
%P 994-999
Markdown (Informal)
[YoungDSMLKZ at SemEval-2026 Task 13: MIL-UniXcoder with Meta-Stacking and Handcrafted Features for AI-Generated Code Detection](https://aclanthology.org/2026.semeval-1.137/) (Gainulla & Shamsadinov, SemEval 2026)
ACL