@inproceedings{rayhan-ruskanda-2026-farhan,
title = "Farhan Nafis Rayhan at {S}em{E}val-2026 Task 13: Supervised Contrastive Learning Approach with Gated Multiclass Decomposition Ensemble Architecture for Code Authorship Identification",
author = "Rayhan, Farhan and
Ruskanda, Fariska",
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-1.431/",
pages = "3485--3494",
ISBN = "979-8-89176-414-9",
abstract = "This paper present our submission for SemEval-2026 Task 13 Subtask B, which requires the multi-class attribution of code snippets across 10 distinct AI generator families and a human baseline. Our proposed system utilizes a three-stage ensemble architecture specifically designed to navigate extreme class imbalance and capture subtle stylometric fingerprints. Initially, we employ Supervised Contrastive Learning to fine-tune a UniXcoder and ModernBERT backbone. Resulting embeddings are then processed by five heterogeneous shallow experts, each utilizing a multiclass decomposition to master specific generator lineages through specialized architectures. A Human Shield acts as a hierarchical safety auditor as an aggressive binary layer of human vs machine. Finally, a Context-Aware Gated Meta-Learner dynamically aggregates these expert opinions into a final predictions. Our experiments reveal that streamlining the system to a pure UniXcoder backbone fine-tuned with supervised contrastive learning improves performance, outclassing the official CodeBERT baseline with a final Macro-F1 score of 0.31389, ranking 26th overall."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="rayhan-ruskanda-2026-farhan">
<titleInfo>
<title>Farhan Nafis Rayhan at SemEval-2026 Task 13: Supervised Contrastive Learning Approach with Gated Multiclass Decomposition Ensemble Architecture for Code Authorship Identification</title>
</titleInfo>
<name type="personal">
<namePart type="given">Farhan</namePart>
<namePart type="family">Rayhan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fariska</namePart>
<namePart type="family">Ruskanda</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>This paper present our submission for SemEval-2026 Task 13 Subtask B, which requires the multi-class attribution of code snippets across 10 distinct AI generator families and a human baseline. Our proposed system utilizes a three-stage ensemble architecture specifically designed to navigate extreme class imbalance and capture subtle stylometric fingerprints. Initially, we employ Supervised Contrastive Learning to fine-tune a UniXcoder and ModernBERT backbone. Resulting embeddings are then processed by five heterogeneous shallow experts, each utilizing a multiclass decomposition to master specific generator lineages through specialized architectures. A Human Shield acts as a hierarchical safety auditor as an aggressive binary layer of human vs machine. Finally, a Context-Aware Gated Meta-Learner dynamically aggregates these expert opinions into a final predictions. Our experiments reveal that streamlining the system to a pure UniXcoder backbone fine-tuned with supervised contrastive learning improves performance, outclassing the official CodeBERT baseline with a final Macro-F1 score of 0.31389, ranking 26th overall.</abstract>
<identifier type="citekey">rayhan-ruskanda-2026-farhan</identifier>
<location>
<url>https://aclanthology.org/2026.semeval-1.431/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>3485</start>
<end>3494</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Farhan Nafis Rayhan at SemEval-2026 Task 13: Supervised Contrastive Learning Approach with Gated Multiclass Decomposition Ensemble Architecture for Code Authorship Identification
%A Rayhan, Farhan
%A Ruskanda, Fariska
%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 rayhan-ruskanda-2026-farhan
%X This paper present our submission for SemEval-2026 Task 13 Subtask B, which requires the multi-class attribution of code snippets across 10 distinct AI generator families and a human baseline. Our proposed system utilizes a three-stage ensemble architecture specifically designed to navigate extreme class imbalance and capture subtle stylometric fingerprints. Initially, we employ Supervised Contrastive Learning to fine-tune a UniXcoder and ModernBERT backbone. Resulting embeddings are then processed by five heterogeneous shallow experts, each utilizing a multiclass decomposition to master specific generator lineages through specialized architectures. A Human Shield acts as a hierarchical safety auditor as an aggressive binary layer of human vs machine. Finally, a Context-Aware Gated Meta-Learner dynamically aggregates these expert opinions into a final predictions. Our experiments reveal that streamlining the system to a pure UniXcoder backbone fine-tuned with supervised contrastive learning improves performance, outclassing the official CodeBERT baseline with a final Macro-F1 score of 0.31389, ranking 26th overall.
%U https://aclanthology.org/2026.semeval-1.431/
%P 3485-3494
Markdown (Informal)
[Farhan Nafis Rayhan at SemEval-2026 Task 13: Supervised Contrastive Learning Approach with Gated Multiclass Decomposition Ensemble Architecture for Code Authorship Identification](https://aclanthology.org/2026.semeval-1.431/) (Rayhan & Ruskanda, SemEval 2026)
ACL