@inproceedings{hegazy-2026-tathabbut,
title = "Tathabbut at at {I}slamic{E}val 2026: Canonical-Provenance Evidence Fusion for Fine-Grained Citation Hallucination Verification",
author = "Hegazy, Salma Khaled",
editor = "Abdul-Mageed, Muhammad and
Elsayed, Tamer and
Bouamor, Houda and
El-Beltagy, Samhaa and
Al-Khalifa, Hend and
Abdelali, Ahmed and
Elmadany, AbdelRahim and
El Mekki, Abdellah and
Darwish, Kareem and
Alkhereyf, Sakhar and
Luqman, Hamzah and
Khalifa, Salam and
Magdy, Samar and
Alyafeai, Zaid and
Hamed, Injy and
Zaghouani, Wajdi and
Zitouni, Imed",
booktitle = "Proceedings of The Fourth {A}rabic Natural Language Processing Conference: Shared Tasks",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.arabicnlp-sharedtasks.132/",
pages = "1075--1080",
ISBN = "979-8-89176-497-2",
abstract = "Islamic question-answering systems can produce fluent Arabic while altering Qur{'}anic wording, Hadith text, narrator chains, or source attribution. We present Tathabbut for two IslamicEval 2026 settings: fine-grained verification and canonical correction. For verification, Canonical-Provenance Evidence Fusion (CPEF) classifies Ayah, matn, isnad, and claimed-source segments by combining canonical retrieval with collection, narrator, response-level, contradiction, and exact-matn provenance evidence. CPEF achieves 0.9452 macro accuracy on the official Test set. For correction, Type-Aware Selective Canonical Retrieval (TASCR) reranks authoritative Qur{'}anic and Hadith candidates using lexical, memory-based, contextual, and source evidence, and abstains when confidence is insufficient. TASCR achieves 86.29{\%} Test accuracy. A post-hoc Development diagnostic finds the gold correction for 319/327 (97.55{\%}) recoverable cases in an expanded candidate pool, indicating that candidate discrimination and abstention are larger bottlenecks than retrieval recall. Neither submitted component invokes a generative LLM at inference time."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hegazy-2026-tathabbut">
<titleInfo>
<title>Tathabbut at at IslamicEval 2026: Canonical-Provenance Evidence Fusion for Fine-Grained Citation Hallucination Verification</title>
</titleInfo>
<name type="personal">
<namePart type="given">Salma</namePart>
<namePart type="given">Khaled</namePart>
<namePart type="family">Hegazy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of The Fourth Arabic Natural Language Processing Conference: Shared Tasks</title>
</titleInfo>
<name type="personal">
<namePart type="given">Muhammad</namePart>
<namePart type="family">Abdul-Mageed</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tamer</namePart>
<namePart type="family">Elsayed</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Houda</namePart>
<namePart type="family">Bouamor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Samhaa</namePart>
<namePart type="family">El-Beltagy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hend</namePart>
<namePart type="family">Al-Khalifa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ahmed</namePart>
<namePart type="family">Abdelali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">AbdelRahim</namePart>
<namePart type="family">Elmadany</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abdellah</namePart>
<namePart type="family">El Mekki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kareem</namePart>
<namePart type="family">Darwish</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakhar</namePart>
<namePart type="family">Alkhereyf</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hamzah</namePart>
<namePart type="family">Luqman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Salam</namePart>
<namePart type="family">Khalifa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Samar</namePart>
<namePart type="family">Magdy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zaid</namePart>
<namePart type="family">Alyafeai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Injy</namePart>
<namePart type="family">Hamed</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wajdi</namePart>
<namePart type="family">Zaghouani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Imed</namePart>
<namePart type="family">Zitouni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-497-2</identifier>
</relatedItem>
<abstract>Islamic question-answering systems can produce fluent Arabic while altering Qur’anic wording, Hadith text, narrator chains, or source attribution. We present Tathabbut for two IslamicEval 2026 settings: fine-grained verification and canonical correction. For verification, Canonical-Provenance Evidence Fusion (CPEF) classifies Ayah, matn, isnad, and claimed-source segments by combining canonical retrieval with collection, narrator, response-level, contradiction, and exact-matn provenance evidence. CPEF achieves 0.9452 macro accuracy on the official Test set. For correction, Type-Aware Selective Canonical Retrieval (TASCR) reranks authoritative Qur’anic and Hadith candidates using lexical, memory-based, contextual, and source evidence, and abstains when confidence is insufficient. TASCR achieves 86.29% Test accuracy. A post-hoc Development diagnostic finds the gold correction for 319/327 (97.55%) recoverable cases in an expanded candidate pool, indicating that candidate discrimination and abstention are larger bottlenecks than retrieval recall. Neither submitted component invokes a generative LLM at inference time.</abstract>
<identifier type="citekey">hegazy-2026-tathabbut</identifier>
<location>
<url>https://aclanthology.org/2026.arabicnlp-sharedtasks.132/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>1075</start>
<end>1080</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Tathabbut at at IslamicEval 2026: Canonical-Provenance Evidence Fusion for Fine-Grained Citation Hallucination Verification
%A Hegazy, Salma Khaled
%Y Abdul-Mageed, Muhammad
%Y Elsayed, Tamer
%Y Bouamor, Houda
%Y El-Beltagy, Samhaa
%Y Al-Khalifa, Hend
%Y Abdelali, Ahmed
%Y Elmadany, AbdelRahim
%Y El Mekki, Abdellah
%Y Darwish, Kareem
%Y Alkhereyf, Sakhar
%Y Luqman, Hamzah
%Y Khalifa, Salam
%Y Magdy, Samar
%Y Alyafeai, Zaid
%Y Hamed, Injy
%Y Zaghouani, Wajdi
%Y Zitouni, Imed
%S Proceedings of The Fourth Arabic Natural Language Processing Conference: Shared Tasks
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-497-2
%F hegazy-2026-tathabbut
%X Islamic question-answering systems can produce fluent Arabic while altering Qur’anic wording, Hadith text, narrator chains, or source attribution. We present Tathabbut for two IslamicEval 2026 settings: fine-grained verification and canonical correction. For verification, Canonical-Provenance Evidence Fusion (CPEF) classifies Ayah, matn, isnad, and claimed-source segments by combining canonical retrieval with collection, narrator, response-level, contradiction, and exact-matn provenance evidence. CPEF achieves 0.9452 macro accuracy on the official Test set. For correction, Type-Aware Selective Canonical Retrieval (TASCR) reranks authoritative Qur’anic and Hadith candidates using lexical, memory-based, contextual, and source evidence, and abstains when confidence is insufficient. TASCR achieves 86.29% Test accuracy. A post-hoc Development diagnostic finds the gold correction for 319/327 (97.55%) recoverable cases in an expanded candidate pool, indicating that candidate discrimination and abstention are larger bottlenecks than retrieval recall. Neither submitted component invokes a generative LLM at inference time.
%U https://aclanthology.org/2026.arabicnlp-sharedtasks.132/
%P 1075-1080
Markdown (Informal)
[Tathabbut at at IslamicEval 2026: Canonical-Provenance Evidence Fusion for Fine-Grained Citation Hallucination Verification](https://aclanthology.org/2026.arabicnlp-sharedtasks.132/) (Hegazy, ArabicNLP 2026)
ACL