Misleading and incongruent news on digital platforms is pivotal in spreading misinformation and disinformation, leading to widespread skepticism and misconception among audiences or content consumers. Existing studies employ similarity-based, summarization-based, and dual summarization methods to detect incongruent news. However, the incongruent news detection methods in existing studies exhibit the following key limitations. 1) Bag-of-words-based methods fail to capture the deep semantic relationships and complex negations between the news body sentences and the headline and between the news body and the headline. 2) Similarity-based methods struggle to detect incongruent news articles with concise headlines and large news bodies. 3) The existing methods in the literature are ineffective in partially incongruent news detection. 4) Methods in the literature are inadequate in handling topic inconsistency between sentences of the news body and topic dissimilarities between headlines and bodies for detecting incongruent articles. To address the aforementioned limitations of existing studies, this work fine-tunes bidirectional encoder representations from transformers (BERT) and robustly optimized BERT pretraining approach (RoBERTa) and proposescascade classificationandmasked language modeling with promptfor detecting misleading and incongruent news articles. We conduct our experiments on four publicly available benchmark datasets, and our results suggest that our proposed models outperform existing state-of-the-art methods in the literature and effectively detect incongruent and fake news of various forms, including misleading, satire, hoax, and propaganda. We also evaluate the robustness of our proposed methods in detecting incongruent and fake news by assessing their performance on a curated dataset of real-world misinformation and incongruent news instances. Our evaluations suggest that the proposed models are highly effective in detecting incongruent and fake news articles across diverse genres.

Headline generation, a crucial task in summarization, aims to summarize an entire article into a concise, single line. Despite the proficiency of sequence-to-sequence encoder-decoder models and transformer-based large language models (LLMs) in text generation and summarization, generating headlines that include numerals representing the numerals in the news body remains a significant challenge. Generating a numeral-aware headline requires the ability of models to solve numerical and mathematical reasoning capabilities to infer relationships between numerals in the news body. Given the challenges in numeral-aware headline generation and numerical reasoning over numerals in news bodies, this study conducts an empirical investigation of LLMs using various strategies, including Pretrained , Few-shot Prompting , and Chain-of-Thought (CoT) Prompting , for numeral-aware headline generation and numerical reasoning for headline generation. Building upon the insights gained from our empirical study on LLMs for numeral-aware headline generation and numerical reasoning, we propose two novel approaches: instruction tuning with LLMs for numeral-aware headline generation and prompt-based masked language modeling for numerical reasoning. We conducted our experiments on the NumHG dataset. We observed that our proposed method outperforms the Pretrained , Few-shot Prompting , and CoT Prompting setups of LLMs, as well as baseline models from the literature, on both numeral-aware headline generation and numerical reasoning tasks. Observations from the experimental results reveal that our proposed Prompt-based Masked Language Modeling significantly improves the performance of small and medium-sized language models on numerical reasoning tasks. We also study the robustness of our proposed models by evaluating their performance in fact-checking numerical claims and performing numerical reasoning for numeral-aware text summarization. Our findings suggest that the proposed Prompt-based Masked Language Modeling approach is also effective for numerical claim verification and numerical reasoning for numeral-aware text summarization.

Verifying scientific claims presents a significantly greater challenge than verifying political or news-related claims. Unlike the relatively broad audience for political claims, the users of scientific claim verification systems can vary widely, ranging from researchers testing specific hypotheses to everyday users seeking information on a medication. Additionally, the evidence for scientific claims is often highly complex, involving technical terminology and intricate domain-specific concepts that require specialized models for accurate verification. Despite considerable interest from the research community, there is a noticeable lack of large-scale scientific claim verification datasets to benchmark and train effective models. To bridge this gap, we introduce two large-scale datasets, SciClaimHunt and SciClaimHunt_Num, derived from scientific research papers. We propose several baseline models tailored for scientific claim verification to assess the effectiveness of these datasets. Additionally, we evaluate models trained on SciClaimHunt and SciClaimHunt_Num against existing scientific claim verification datasets to gauge their quality and reliability. Furthermore, we conduct human evaluations of the dataset’s claims and perform error analysis to assess the effectiveness of the proposed baseline models. Our findings indicate thatSciClaimHunt and SciClaimHunt_Num serve as highly reliable resources for training models in scientific claim verification.

With the increase in misinformation across digital platforms, incongruent news detection is becoming an important research problem. Earlier, researchers have exploited various feature engineering approaches and deep learning models with embedding to capture incongruity between news headlines and their respective bodies. Studies have broadly considered different combinations of bag-of-words-based features, sequential encoding, hierarchical encoding, headline-guided attention-based encoding, and so on, of the text in headlines and bodies. In this article, we focus on addressing two important limitations observed with hierarchical encoding and headline-guided attention-based encoding methods. The existing hierarchical encoding-based studies limit the hierarchical structure of the body of a news article to paragraph level only, undermining the importance of incorporating long-term dependence from word level to sentence, paragraph, and body. Furthermore, the existing headline-guided attention-based encoding focuses on contextually similar contents in the body of the headline, undermining the importance of incorporating contextually dissimilar contents. Motivated by the above observations, this article proposes a gated recursive and sequential deep hierarchical encoding (GraSHE) method for detecting incongruent news articles by extending the hierarchical structure of the news body from the body to the word level and incorporating incongruity weight. From various experimental setups over three publicly available benchmarks datasets, the experimental results indicate that the proposed model outperforms baseline models with bag-of-word-based features, sequential, hierarchical, and headline-guided attention-based encoding methods. To further validate the performance of the proposed model, we conduct several ablation studies. The following key observations can be made from the ablation study: 1) models with hierarchical encoding outperform models with nonhierarchical encoding; 2) recursive encoding of sentences boosts the performance of models as compared with sequential encoding of sentences within paragraphs; and 3) incongruent news article detection is domain-dependent. Incorporating explicit features further boosts the performance of proposed model and also decreases the domain dependence of models.

The prevalence of incongruent news has demonstrated its significant role in propagating fake news, which catalyzes the dissemination of both misinformation and disinformation. Consequently, detecting incongruent news articles is an important research problem to counter early spreading of misinformation. In the literature, researchers have explored various bag-of-word-based features, news body-centric and news headline-centric encoding methods for incongruent news article detection. However, headline-centric and body-centric approaches in the literature fail to detect partially incongruent articles efficiently. Motivated by the above limitations, this study proposes graph-based dual context matching (GDCM), which first represents headlines and news bodies as abigramnetwork to capture contextual relations between words and document structure. For every word in the headline, GDCM extracts dual contexts (positive and negative) from thebigramnetwork representing news body and estimates similarity between dual contexts and the headline for incongruent news detection. We conduct extensive experiments on three publicly available benchmark datasets and compare its performance with 16 baseline models. Our experimental results suggest that the proposed model outperforms existing state-of-the-art models and efficiently detects partially incongruent news. We further validate the performance of the proposed model through several ablation studies. The following key observations can be made from the ablation studies: 1) extracting dualbigramcontext of words in the headline from different segments of news body and then estimating the similarity between dualbigramcontexts from news body and the headline helps in incongruent news detection and also helps in detecting partial incongruent news efficiently; and 2) representing news headlines and bodies in the form of a network based onbigramcontext helps to capture better nonlinear and contextual relationships between headline and body.

This demonstration presents a database system called GRACEfor storageand retrieval of graphstructures. Structural queries are supported which retrieve graphs based on approximate subgraph isomorphism. Since subgraph isomorphism is NP-complete, GRACE performs retrieval based on inexact graph matching. The underlying model is of a concept called “Vectorization of Structure” that represents structural features of member graphs as vectors in one or more hypothetical spaces. Queries are mapped onto regions in these spaces. Query results is a ranked union of the set of all points lying in the query regions. The implementation displays a GRACE model implemented for storage and retrieval of molecular structures of organic chemicals.

Ethernet -like local area network links have been studied by a number of researchers. Most of these studies have involved extensive simulation models operating at the level of individual packets. However, as we begin building models of systems built around such links, detailed simulation models are neither necessary, nor cost-effective. Instead, a simple analytical model of the medium should be adequate as a component of the higher level system models. This paper discusses a number of analytical models and identifies a last-in-first-out M/G/1 model with slightly increased service time as one which adequately captures both the mean and the coefficient of variation of the response time. Given any offered load, this model can be used to predict the mean waiting time and its coefficient of variation. These two can be used to construct a suitable 2 stage hyperexponential distribution. Random numbers can then be drawn from this distribution for use as waiting times of individual packets.