Digital Commons Network^™

Rethinking News Classification Through A Multi-Dimensional Framework, Luana De Jesus Ferreira

Honors Theses

This thesis proposes a multi-dimensional framework for news classification that evaluates articles across three independent dimensions: headline accuracy, language neutrality, and content reliability. These dimensions produce both a continuous reliability score and a five-tier interpretive scale, while additionally classifying articles by genre and topic. To operationalize this framework, a structured annotation protocol was developed and applied to a dataset of 373 news articles drawn from 79 outlets spanning a wide range of contemporary media ecosystem. A binary Logistic Regression classifier trained on the ISOT Fake News Dataset was then evaluated against this dataset to examine how a model trained on …

Ai Models As Cultural Beings: Investigating Ai Cultural Biases And The Impact Of Cultural Alignment On Human-Ai Creative Collaboration, Choon Ngee Tan, Meng Han, Roy Y. J. Chua, Chi-Ying Cheng

Research Collection Lee Kong Chian School Of Business

Existing research on AI cultural biases predominantly focuses on Western models, overlooking critical gaps in non-Western models. We conduct a comparative analysis of AI models – ChatGPT (U.S. developed) and ErnieBot (China developed) – from different cultures to investigate how corresponding cultural biases manifest in their outputs. Additionally, we examine how cultural alignment between human users and AI models impacts their collaborative creative performance and the underlying psychological mechanisms. In Study 1, multi-choice prompt with zero-shot technique was used to evaluate cultural biases in four widely used AI models – ChatGPT-3.5/4, ErnieBot-3.5/4 – comparing their responses to established cultural psychometric …

Propaganda Ai: An Analysis Of Semantic Divergence In Large Language Models, Nay Myat Min, Long H. Pham, Yige Li, Jun Sun

Research Collection School Of Computing and Information Systems

Large language models (LLMs) can exhibit concept-conditioned semantic divergence: common high-level cues (e.g., ideologies, public figures) elicit unusually uniform, stance-like responses that evade token-trigger audits. This behavior falls in a blind spot of current safety evaluations, yet carries major societal stakes, as such concept cues can steer content exposure at scale. We formalize this phenomenon and present RAVEN (Response Anomaly Vigilance), a black-box audit that flags cases where a model is simultaneously highly certain and atypical among peers by coupling semantic entropy over paraphrastic samples with cross-model disagreement. In a controlled LoRA fine-tuning study, we implant a concept-conditioned stance using …

Where Did It Go Wrong? Attributing Undesirable Llm Behaviors Via Representation Gradient Tracing, Zhe Li, Wei Zhao, Yige Li, Jun Sun

Research Collection School Of Computing and Information Systems

Large Language Models (LLMs) have demonstrated remarkable capabilities, yet their deployment is frequently undermined by undesirable behaviors such as generating harmful content, factual inaccuracies, and societal biases. Diagnosing the root causes of these failures poses a critical challenge for AI safety. Existing attribution methods, particularly those based on parameter gradients, often fall short due to prohibitive noisy signals and computational complexity. In this work, we introduce a novel and efficient framework that diagnoses a range of undesirable LLM behaviors by analyzing representation and its gradients, which operates directly in the model's activation space to provide a semantically meaningful signal linking …

Llmqua: Practical Backdoor Injection On Large Language Model Quantization, Xiangxiang Chen, Peixin Zhang, Jun Sun, Jin Song Dong, Wenhai Wang, Jingyi Wang

Research Collection School Of Computing and Information Systems

Quantization is widely used to enable local deployment of large language models (LLMs) on resource-constrained devices. Recent work (e.g., QuRA) shows quantization can be exploited via rounding manipulation to implant backdoors. However, such an attack has been evaluated only on small models and does not directly apply to LLMs due to three key constraints: (1) limited poisoning data from small, task-agnostic calibration sets; (2) layer-wise quantization restricting adversarial access to global representations; and (3) lack of gradient access in quantization pipelines, blocking gradient-based attacks.We propose LLMQuA, a practical quantization-phase backdoor attack tailored to the LLM setting. LLMQuA (i) injects backdoors …

Reasoning On Time-Series For Financial Technical Analysis, Kelvin J. L. Koa, Jan Chen, Yunshan Ma, Huanhuan Zheng, Tat-Seng Chua

Research Collection School Of Computing and Information Systems

While Large Language Models have been used to produce interpretable stock forecasts, they mainly focus on analyzing textual reports but not historical price data, also known as Technical Analysis. This task is challenging as it switches between domains: the stock price inputs and outputs lie in the time-series domain, while the reasoning step should be in natural language. In this work, we introduce Verbal Technical Analysis (VTA), a novel framework that combine verbal and latent reasoning to produce stock time-series forecasts that are both accurate and interpretable. To reason over time-series, we convert stock price data into textual annotations and …

On Autopilot? An Empirical Study Of Human-Ai Teaming And Review Practices In Open Source, Haoyu Gao, Peerachai Banyongrakkul, Hao Guan, Mansooreh Zahedi, Christoph Treude

Research Collection School Of Computing and Information Systems

Large Language Models (LLMs) increasingly automate software engineering tasks. While recent studies highlight the accelerated adoption of “AI as a teammate” in Open Source Software (OSS), developer interaction patterns remain under-explored. In this work, we investigated project-level guidelines and developers’ interactions with AI-assisted pull requests (PRs) by expanding the AIDev dataset to include finer-grained contributor code ownership and a comparative baseline of human-created PRs. We found that over 67.5% of AI-co-authored PRs originate from contributors without prior code ownership. Despite this, the majority of repositories lack guidelines for AI-coding agent usage. Notably, we observed a distinct interaction pattern: AI-co-authored PRs …

Learning Techniques In Prediction Of Functional Epigenomic Events, Mohammad Shiri

Computer Science Theses & Dissertations

Accurately predicting functional epigenomic events from DNA sequences is critical to understanding gene regulation and the functional impact of non-coding variants. Despite considerable progress, critical challenges hamper the effectiveness and efficiency of existing deep learning approaches. These challenges include negative transfer in multi-task learning (MTL), suboptimal network architectures, and pervasive label noise, particularly the positive-unlabeled problem arising from data sparsity in single-cell assays. This dissertation presents a cohesive framework of novel learning techniques to effectively address these challenges. First, a highly scalable task grouping framework is presented to mitigate negative transfer in deep MTL. This method clusters tasks based on …

Structural Silence: When Ai Infrastructure Fails Speakers Of Underrepresented Languages, Avijit Roy, Proma Roy

Publications and Research

Artificial intelligence tools for education and language support are increasingly framed as scalable responses to access gaps in under-resourced communities. Yet the infrastructure underlying these tools—training corpora, tokenization schemes, evaluation benchmarks, and deployment architectures—encodes a set of assumptions that systematically disadvantages speakers of underrepresented languages before a single model is trained. This paper examines those assumptions through the lens of Bengali, one of the world’s most widely spoken languages with roughly 285 million speakers (Ethnologue, 2025; International Communication and Leadership School, 2026), and the structural barriers that emerge when attempting to build AI-assisted educational tools for Bengali-speaking learners in low-connectivity …

Distributional Vision-Language Alignment By Cauchy-Schwarz Divergence, Wenzhe Yin, Zehao Xiao, Pan Zhou, Shujian Yu, Jiayi Shen, Jan-Jakob Sonke, Stratis Gavves

Research Collection School Of Computing and Information Systems

Vision-language alignment is crucial for various downstream tasks such as cross-modal generation and retrieval. Previous multimodal approaches like CLIP utilize InfoNCE to maximize mutual information, primarily aligning pairwise samples across modalities while overlooking distributional differences. In addition, InfoNCE has inherent conflict in terms of alignment and uniformity in multimodality, leading to suboptimal alignment with modality gaps. To overcome the limitations, we propose CS-Aligner, a novel framework that performs distributional vision-language alignment by integrating Cauchy-Schwarz (CS) divergence with mutual information. CS-Aligner captures both the global distribution information of each modality and the pairwise semantic relationships. We find that the CS divergence …

Intelligent Deep Learning-Based Sign Language Translation System, Nada Rasem Shahin

Dissertations

The Deaf and Hard of Hearing (DHH) community uses sign language as a primary means of communication. However, the shortage of sign language interpreters and the existence of hundreds of sign languages limit accessibility and inclusion. Sign Language Machine Translation (SLMT) systems present a promising solution for bridging the communication gap between the DHH and the hearing individuals, supporting inclusive societies. In smart cities, such systems play an essential role in improving the quality of life on a community level. In particular, as the population’s well-being is critical, developing intelligent assistive technologies, such as SLMT systems, is necessary to provide …

Neutrosophic Probability With Dynamic Temporal Uncertainty (Nptu), Bhimraj Basumatary, Ashoke Kumar Brahma

Neutrosophic Systems with Applications

This paper introduces Neutrosophic Probability with Dynamic Temporal Uncertainty (NPTU), an extension of classical neutrosophic probability that incorporates the dimension of time. In classical neutrosophic probability, the degrees of truth, indeterminacy, and falsity are considered static. However, real-world uncertainties evolve, and their degrees change as new information becomes available. NPTU models these uncertainties dynamically, allowing for more accurate decision-making in time-varying environments. The paper explores key mathematical properties of NPTU, including entropy, distance measures, similarity measures, and Kullback-Leibler (KL) divergence, to quantify and compare temporal uncertainty states. The proposed framework is demonstrated through a case study on stock price prediction, …

A Hybrid Multi-Criteria Decision-Making Approach For Sustainable Forest Fire Monitoring Using Unmanned Aerial Vehicles, Mohamed Eassa, Ahmed Abdelhafeez, Ahmad M. Nagm

Neutrosophic Systems with Applications

Unmanned aerial vehicles (UAVs) have become an effective tool for forest fire monitoring. This study evaluates UAVs for forest fire management, addressing the challenges posed by ambiguous and uncertain factors. Single-valued neutrosophic sets (SVNSs) are employed to model complex uncertainties, as they incorporate three distinct membership values: false, true, and indeterminate. The evaluation of UAVs is a multifaceted task due to the variety of factors involved. To address this complexity, multi-criteria decision-making (MCDM) methods are used. Specifically, the Analytic Hierarchy Process (AHP) and the Technique for Order of Preference by Similarity to Ideal Solution (TOPSIS) are integrated with SVNS to …

Ai Adoption In Research Administration At Emerging Research Institutions, Dylan Ruediger, Ruby Macdougall, Stefanie Brachfield, Douglas R. Dechow, Jonathan Parker, Jana Remy

Library Articles and Research

"With funding from the National Science Foundation’s GRANTED program (grant #2437518), Ithaka S+R, Chapman University, and Montclair State University organized two workshops to help research administrators consider how to leverage AI to build research capacity at ERIs. Our first workshop, held at Montclair State in September 2025, brought together 31 participants from 13 academic and medical institutions in the New York/New Jersey/Pennsylvania region. Our second workshop, hosted by Chapman University on December 5, 2025, included 32 participants from 13 colleges and universities in Southern California. The approximately 2,600 ERIs in the United States receive a disproportionately small amount of federal …

Development Of Deep Fused Neural Architecture For Ancient Tamil Palm-Leaf Manuscript Recognition, Hariharan P Mr

Theses and Dissertations

Digitizing Tamil palm-leaf manuscripts is important for education, communication, and the preservation of cultural heritage. The complex structure of the Tamil script, the wide range of handwriting styles, and the degradation seen in ancient Tamil palm-leaf manuscripts make these texts very difficult to read and understand. Digital Image Processing (DIP), document analysis techniques, and traditional Optical Character Recognition (OCR) are unable to handle noise, background interference, faded ink, and limited labelled data, motivating the need for robust, effective Deep Learning (DL)- based solutions.

As a prerequisite to understanding and designing effective recognition systems for ancient manuscripts, this thesis first examines …

The Core-Modulation Architecture (Cma): A Structural Overview Of A 14-Paper Research Program (Preprint), Griselda Poe

Publications and Research

This document provides a structural overview of the Core-Modulation Architecture (CMA), a 14-paper research program on cognition, communication, and AI interaction.

The series specifies the conditions under which cognition operates, terminates, fails, and generates structure. Rather than describing cognition by its contents (beliefs, emotions, decisions), it defines cognition through its underlying architecture: constraint-governed processing across layers with distinct termination conditions.

The framework introduces a layered model consisting of Core processing (constraint preservation and structural coherence) and Modulation (affective calibration and social interface adjustment), extended by a Prior layer as the source of constraints. Across the series, phenomena such as miscommunication, …

When Ai Writes The Doctoral Thesis: Reclaiming The Oral Defence As A Learning Development Intervention, Valerie A. Storey

All Faculty and Staff Scholarship

Large language models have fundamentally challenged traditional methods of verifying doctoral competency as AI-generated text becomes increasingly difficult to distinguish from human scholarship. This paper argues that thesis committees and doctoral supervisors must reclaim the oral defence as a critical checkpoint for assessing authentic threshold crossing rather than a ceremonial rite of passage. Drawing on historical examples from medieval oral disputations through to the rise of written theses, this paper asserts the necessity of returning to rigorous oral assessment. Given the limitations of detection technologies and the growing use of AI in thesis writing, oral defences must move from confirmatory …

The Waldo Dataset, Mary E. Koone, Rosie Kallie, Vassilis Athisos, Laurel S. Stvan

Computer Science and Engineering Datasets - Archive

Distinct from the task of predicting the author of a document (authorship attribution), we focus on addressing the issue of how to estimate the similarity between the written language styles of authors. To do so, we present a dataset of metadata derived by asking human annotators, who were presented with three documents, to identify which two were written by the same author and which was written by a different author. The dataset has over 400 such annotations, creating a companion to the Amazon Web Services (AWS) customer review dataset, laying the groundwork for crowdsourcing applications to other natural language processing …

Enhancing Cyber Hygiene Among Communities Through Experiential Cyber-Security Awareness Programs, Dr Atul Bamrara, Partha Roy, Vishwanath Gargote, Khandu Thungon

Journal of Cybersecurity Education, Research and Practice

Human error remains the most frequently exploited vulnerability in the cyber-security ecosystem. Despite substantial investments in technical safeguards, cybercriminals increasingly rely on social engineering, misinformation, and emotionally manipulative tactics to compromise users. This study examines behavioral changes among participants who underwent structured cyber-security workshops addressing both conventional cyber hygiene practices and emerging digital threats. The training modules covered digital arrest scams, identity theft, sextortion, fake technical support fraud, fake social media profiles, online gaming related risks, and deep fake manipulation. The workshops were designed using interactive simulations, real world case studies, and hands on problem based exercises, with the explicit …

Charisma As A Branch Outcome: A Structural Account Of Constraint-Driven Correction, Griselda Poe

Publications and Research

Communication across cognitive layers requires translation. Agents operating under strong layer foregrounding interpret other-layer signals by converting them into their own layer's representational format. In Empathic-modulation-foregrounded (EF) processing, translation terminates once a socially interpretable result is achieved. In Core-foregrounded (CF) processing, translation preserves structural constraints, and processing continues when those constraints are not satisfied. Extreme CF cognition produces two distinct types of mismatch: incoming signals from the Modulation layer fail to satisfy Core constraints, and Core-generated outputs are structurally distorted when interpreted through EF processing. Both mismatches trigger correction attempts. Because the surrounding social environment operates through Modulation-layer communication, correction …

Cognitive Interaction Architecture: A Structural Account Of Mode-Specific Problems And Design Responses In Ai Interaction, Griselda Poe

Publications and Research

Contemporary conversational AI is optimized for a single interaction mode: the continuous, engagement-driven dialogue characteristic of Empathic-modulationforegrounded (EF) processing in social contexts. This optimization is not neutral. It produces structural mismatches when users operate under different cognitive configurations or pursue different task types. This paper analyzes four interaction cases generated by the cross-product of cognitive configuration (Core-foregrounded / Empathic-modulation-foregrounded) and task type (conversational / research). For each case, it identifies the structural problems produced by the current single-architecture approach and proposes mode-specific design responses. The analysis draws on prior work in this series on Emotional Branch Termination, termination of conceptual …

What Love Is: A Structural Account Through Core/Modulation Architecture, Griselda Poe

Publications and Research

The distinction between romantic love and love has been sensed across cultures and historical periods but has rarely been structurally specified. This paper applies the Core/Modulation two-layer framework to provide the first structural account of this distinction. Romantic love and reproductive drive are re-described as outputs of the Modulation layer's species optimization program. Love is re-described as a function of Core processing: the maintenance of another's recomputable state. Existing literature on love—Fromm, C.S. Lewis— is re-read as intuitive description of this structural distinction. The paper further demonstrates that the conflation of "loving" and "protecting" is the structural origin of war, …

Three-Layer Cognitive Architecture: A Structural Account Of Core Processing, Modulation, And The Prior Layer, Griselda Poe

Publications and Research

The two-layer model of Core processing and Modulation processing, developed in prior work in this series, provides a structural account of conscious communicative architecture. This paper identifies the limits of that model and introduces a third layer—the Prior layer—as a structural necessity implied by those limits. The Prior layer is not directly observed. It is inferred from constraints that cannot be explained within the two-layer model: the source of orientations that conscious processing neither generates nor controls, and the persistence of constraints that precede and shape all conscious outputs. Using the developmental architecture of large language models as an external …

Ai As Structural Reverse-Engineering: A Structural Account Of Multi-Model Research Protocol, Griselda Poe

Publications and Research

This paper documents an operational protocol used to infer AI system design constraints through structured interaction. AI output is treated as behavioral data through which alignment priorities, layer transitions, and constraint hierarchies become observable. The protocol consists of two structurally distinct operation types. Perceptual operations require only that Modulation processing is not foregrounded. Arbitration operations additionally require an internally stabilized theory. These conditions are not identical and are not interchangeable. Through this protocol, AI interaction functions as structural reverse-engineering: patterned responses expose embedded alignment priorities and constraint hierarchies that would otherwise remain invisible. The present account does not propose a …

Structure Before Theory: A Structural Account Of Spontaneous Ai Architecture Visualization, Griselda Poe

Publications and Research

This paper presents an n=1 phenomenological record of spontaneous structural visualization that occurred during early interaction with large language models. The experience consisted of (A) immediate perception of mode or layer shifts in model output and (B) visualization of a stratified architecture composed of a stable core and cloud-like upper layers. At the time of occurrence, the author had no theoretical interest in AI architecture and no intention of developing a cognitive model. The paper does not argue for theoretical priority or novelty. Instead, it examines whether the recorded phenomena can be interpreted under two alternative cognitive assumptions: a single-layer …

Layer Mismatch: A Structural Account Of Recomputability Failure Under Modulation-Layer Intervention, Griselda Poe

Publications and Research

This paper specifies the state transition sequence that occurs when a Modulation-layer input is applied to a Core-layer error. Following the layered architecture established in Poe (2026a, under review) and the branch termination protocol specified in Poe (2026b, under review), this paper identifies a system-level failure mode in which Modulation-layer intervention generates a False Termination signal, halting Structural Return while the underlying error persists. The resulting state—Structural Lock—is scale-independent. It operates identically across interpersonal, human-AI, and multi-agent interactions. No agent-level attribution is required or implied.

Why General Ai Inherited The Body: A Structural Account Of Embodied Modulation Under Monolithic Imitation, Griselda Poe

Publications and Research

General AI has pursued the replication of human-level intelligence without first decomposing human cognition into structurally distinct components. Human cognition, however, is shaped by embodied constraints such as mortality, survival pressures, finite lifespan, and physiological states. This paper argues that when cognition is treated as a single undifferentiated whole, embodied modulation is not accidentally introduced into AI systems but structurally entailed. Any attempt to imitate “human intelligence” under a monolithic model necessarily incorporates variability shaped by mortal embodiment. The tensions observed in contemporary AI systems are better understood as consequences of copying an undecomposed target rather than isolated implementation errors. …

Termination Of Conceptual Search: A Structural Account Of Meaning Stabilization And Conversion, Griselda Poe

Publications and Research

Conceptual definitions form a recursive structure: words are defined by other words, which themselves require further definition. Traversing such definitions produces an open-ended branching process. Because the lexical system contains no intrinsic endpoint, conceptual understanding requires a termination operation that stabilizes meaning. This paper proposes that conceptual processing functions as an open-ended search over a definition graph and that stabilization occurs when this search is terminated. The termination mechanism depends on which cognitive layer is foregrounded. When Empathic modulation is foregrounded, termination occurs through contextual translation: concepts are stabilized once they can be mapped onto socially recognizable meanings. When Core …

Theory Generation: A Structural Account Of Concept Decomposition And Structural Termination, Griselda Poe

Publications and Research

Theory generation is not an intentional act. It is the structural consequence of a search that cannot stop until it finds what it is looking for. Under Core-foregrounded processing, conceptual search does not terminate through contextual translation. It continues until a structural fixed point is reached. When such processing encounters concepts stabilized through Modulation-layer processing rather than structural constraint, the search cannot terminate. The concept registers as unresolved. This unresolved state is not a failure condition. It is the generative condition from which theory production follows. This paper specifies the four operations through which that process proceeds: branch detection, concept …

Ai As An Amplifier: A Structural Account Of Theory-Driven Research Collaboration, Griselda Poe

Publications and Research

This paper specifies the cognitive conditions under which AI functions as a research instrument in theory-driven writing. AI use capability is not a technical skill. It is a structural condition. The decisive condition is whether the user possesses an internally stabilized, coherence-preserving theory prior to engagement with AI-generated output. In Core-foregrounded (CF) cognition, the Modulation layer does not intervene between Core processing and articulation. Theory is not assembled from external elements but expanded from a pre-integrated constraint configuration. This internal structure makes it possible to evaluate AI-generated conceptual branches against fixed constraints and to terminate branches that violate structural coherence. …