[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-82827-en":3,"doc-seo-82827-105":30,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":20,"is_deleted":4,"is_public":21,"is_downloadable":21,"audit_status":21,"page_count":22,"language":23,"language_code":24,"site_id":25,"html_lang":24,"table_of_contents":26,"faqs":27,"seo_title":13,"seo_description":14,"update_tm":28,"read_time":29},82827,5909877438554,"Maeve","https://ap-avatar.wpscdn.com/avatar/5600025385ad2bf12a7?_k=1778553567797529272",8,"Research & Report","Can Temporal Article-Level Credibility Signals Improve Domain-Level Credibility Prediction","Web domain credibility evaluation is essential for combating misinformation, yet newly emerging domains remain difficult to judge because they lack reputation history. Expert fact-checkers assess credibility by examining article content for misinformation, bias, and propaganda, but large-scale LLM-driven content generation makes manual review impractical. This paper proposes the Domain Credibility Evaluation Framework (DCEF), a temporal, expert-ratings-grounded workflow that infers domain credibility from published articles alone, using time-stamped evidence without prior domain knowledge.","Can temporal article-level credibility signals improve domain-level  \ncredibility prediction?  \nIslam Eldifrawi and Shengrui Wang and Amine Trabelsi  \n@[usherbrooke.ca](usherbrooke.ca)  \narXiv :2607 .04560v 1 [ cs .CL] 6 Jul 2026  \nAbstract  \nWeb domain credibility evaluation is vital for combating misinformation. It is conducted by examining factors such as domain type, transparency, and overall reputation. However, assessing the credibility of newly emerging web domains remains challenging since they have no reputation yet. Expert fact-checkers evaluate the credibility of domains by analyzing the content of their articles, including the presence of misinformation, bias, or propaganda. Yet, the ease of large-scale content generation enabled by LLMs has accelerated the creation of new content, rendering manual assessment insufficient and underscoring the need for automated approaches to domain credibility evaluation. In this paper, we introduce our Domain Credibility Evaluation Framework (DCEF), a temporal framework for domain credibility evaluation grounded in expert ratings. DCEF enables us to investigate whether the credibility of web domains can be assessed from their published articles following the workflow of expert fact-checkers, without any prior knowledge of the source domains themselves.  \n1 Introduction  \nAssessing the credibility of the information source is vital in fact-checking (Eldifrawi et al., 2024 ; Guo et al., 2022) . Due to recent advances in content generation, new domains are being created atan unprecedented pace, and most of them don’t disclose their content generation methods. Manual evaluation of these domains credibility is infeasible. Automating the credibility assessment of these domains based on their content has become essential since they have no reputation yet.  \nGNNs and pure graph-based approaches struggle to evaluate newly emerging domains with no historical data, or activity due to the “cold-start problem.”Since GNNs depend on connections between nodes, an isolated domain lacks the relational information needed for evaluation (Frej et al., 2024) .  \n\n| Area | Open Gap |\n| --- | --- |\n| Generalization | Contextual adaptation |\n| Bias & Fairness | Political/ ideological bias mitigation |\n| Dynamics | Temporal credibility evaluation |\n| Insight | Presence of model justification |\n\nTable 1: Gaps in domain credibility evaluation models (Srba et al., 2024) .  \nCredibility (Believability) is assessed from content through a variety of heuristics known as credibility signals, which help evaluate the overall trustworthiness of information sources (Leite et al., 2025) . These signals include the presence of bias, propaganda, misinformation, or misalignment between in article titles and their content.  \nCredibility signals can be categorized as subjective or objective indicators(Srba et al., 2024) . Subjective indicators include aspects such as the design of a webpage, and domain popularity. While these features may influence user perception of credibility, they are not necessarily reliable measures of content quality. In contrast, objective indicators provide stronger evidence of quality and include the presence of bias, propaganda, misleading information, and the number of backlinks.  \nRecent deep learning models, like BERT-style transformers, when fine-tuned on misinformation corpora, often achieve high in-domain accuracy but tend to generalize poorly across different domains. For instance, a model trained on political news may perform poorly when applied to health misinformation (Srba et al., 2024) . In addition, they lack justifications for their classification.  \nLLMs have shown superior cross-domain performance compared to supervised baselines (Srba et al., 2024) . However, LLMs also have notable limitations. Their credibility judgments only moderately align with expert assessments (Spearman correlation nearly 0.50) (Yang and Menczer, 2025a) . In addition, they tend to assign higher credibility","cbCaiffOz5YLuGbh","https://ap.wps.com/l/cbCaiffOz5YLuGbh","pdf",782264,2,1,21,"English","en",105,"# Introduction\n## Key Challenges and Open Gaps\n## Proposed Contributions (DCEF)","[{\"question\":\"Why is domain-level credibility prediction hard for newly emerging web domains?\",\"answer\":\"New domains lack historical reputation data, creating a cold-start situation and making manual assessment infeasible at scale. They also often do not disclose content-generation methods, while automated systems must rely only on available content.\"},{\"question\":\"What is the main idea behind the Domain Credibility Evaluation Framework (DCEF)?\",\"answer\":\"DCEF evaluates domain credibility using time-stamped, article-level evidence in a workflow modeled after expert fact-checkers. The framework outputs credibility ratings without prior knowledge of the domain name, relying solely on the set of articles and their publication dates.\"},{\"question\":\"How does DCEF address limitations of existing models and datasets?\",\"answer\":\"DCEF incorporates temporal dynamics by emphasizing recent articles, addressing gaps where credibility changes over time. It also targets dataset issues such as broken links by constructing a dataset with article content and repairing the accessibility problem.\"}]",1784183228,53,{"code":4,"msg":31,"data":32},"ok",{"site_id":25,"language":24,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"can-temporal-article-level-credibility-signals-improve-domain-level-credibility-prediction","",{"@graph":36,"@context":85},[37,53,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,47,50],{"item":41,"name":42,"@type":43,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":20},"https://docshare.wps.com/document/","Document",{"item":48,"name":12,"@type":43,"position":49},"https://docshare.wps.com/document/research-report/",3,{"item":51,"name":13,"@type":43,"position":52},"https://docshare.wps.com/document/can-temporal-article-level-credibility-signals-improve-domain-level-credibility-prediction/82827/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":24,"description":14,"dateModified":61,"datePublished":62,"encodingFormat":60,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":41,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-07-24","2026-07-16",true,{"@type":65,"interactionType":66,"userInteractionCount":20},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"Why is domain-level credibility prediction hard for newly emerging web domains?","Question",{"text":75,"@type":76},"New domains lack historical reputation data, creating a cold-start situation and making manual assessment infeasible at scale. They also often do not disclose content-generation methods, while automated systems must rely only on available content.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What is the main idea behind the Domain Credibility Evaluation Framework (DCEF)?",{"text":80,"@type":76},"DCEF evaluates domain credibility using time-stamped, article-level evidence in a workflow modeled after expert fact-checkers. The framework outputs credibility ratings without prior knowledge of the domain name, relying solely on the set of articles and their publication dates.",{"name":82,"@type":73,"acceptedAnswer":83},"How does DCEF address limitations of existing models and datasets?",{"text":84,"@type":76},"DCEF incorporates temporal dynamics by emphasizing recent articles, addressing gaps where credibility changes over time. It also targets dataset issues such as broken links by constructing a dataset with article content and repairing the accessibility problem.","https://schema.org",{"og:url":51,"og:type":87,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":89,"canonical":51},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,135],{"id":21,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":20,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]