Digital Commons Network^™

Obstructions To Some Injective Oriented Colourings, Russell J. Campbell, Nancy E. Clarke, Gary Macgillivray

Theory & Applications of Graphs

Each of several possible definitions of local injectivity for a homomorphism of an oriented graph $G$ to an oriented graph $H$ leads to an injective oriented colouring problem. For each case in which such a problem is solvable in polynomial time, we identify a set $\mathcal{F}$ of oriented graphs such that an oriented graph $G$ has an injective oriented colouring with the given number of colours if and only if there is no $F \in \mathcal{F}$ for which there is a locally-injective homomorphism of $F$ to $G$.

Flip It And Reverse It: Probing Consistency Of Llm World Knowledge Under Logical Transformations, Rhianna Smith

Computer Science Senior Theses

When assessing the extent to which someone truly understands the topics they discuss, you might ask them a series of questions that examine their knowledge from different angles. As Large Language Models (LLMs) are increasingly integrated into real-world tasks, they are often required to reason through ambiguous and uncertain scenarios that rarely have a single correct answer. In these settings, their usefulness is contingent on more than accuracy alone. Rather, it depends on the strength of the reasoning that underlies their responses. This begs the question: how might we extend these types of tests to LLMs? We formalize this informal …

Investigating How Llm Trading Agents Integrate External Signals, Rohan Ray

Computer Science Senior Theses

Large Language Models are increasingly deployed in systems that assume more information leads to better decisions: RAG pipelines inject retrieved documents, tool-augmented agents call external APIs, and multi-model architectures route signals between specialized components. Whether this holds when both the information and the outcomes are noisy, and decisions compound over time, has received limited empirical attention. This thesis tests that assumption on LLM-based trading agents. Using StockBench (Chen et al., 2025) as our benchmark, we ran 150 backtests across 2 frontier LLMs (Kimi K2 and Qwen3-235B-Instruct), 12 augmentation strategies, and 5 random seeds, over 82 trading days — a period …

Recognizing And Rewarding Peer Review: Rethinking Research Assessment For Openness, Fairness, And Global Equity, Tung Tung Chan, Bernd Pulverer, Johan Rooryck

FORCE 2026

The Coalition for Advancing Research Assessment (CoARA) Working Group on Recognizing and Rewarding Peer Review has developed a comprehensive framework for reforming how scholarly review is valued within research careers. Our recommendations address a fundamental question: how can peer review, a critical yet often invisible scholarly contribution, be made visible, credited, and meaningfully integrated into research assessment?

Developed through a collaborative effort across 16 European organisations, the Working Group’s outputs offer targeted recommendations for four key stakeholder groups: research performing organizations, research funding bodies, publishers and editors, and individual researchers. These recommendations are structured across five key dimensions:
(1) Openness: …

Open Research Information - How To Support Publishers To Make Metadata Openly Availble, Bianca Kramer

FORCE 2026

Research information, or scholarly metadata, is important for decision making around strategic priorities, distribution of resources, and evaluation of researchers and institutions. It is also used to assess the effect of policies, and to find and assess research results. Open research information (free to access and free to (re)use) is increasingly valued for fair assessment and equitable decision making, and is also important in digital sovereignty.


The Barcelona Declaration on Open Research Information calls on organizations performing, funding and evaluating research to make openness of research information the default, work with services and systems that support and enable open research …

Biologically Informed Negative Samplingfor Antibody Chain Pairing Classification, Ishita Singh

Computer Science Senior Theses

Antibody heavy and light chain (H/L) pairing is fundamental to antigen recognition and stability. While single-cell sequencing preserves native pairing information, widely used bulk repertoire and spatial transcriptomics platforms do not, motivating the need for efficient ML methods to infer H/L pairing. Training a binary classifier for this task faces the methodological challenge of a lack of true biological negatives, since natural selection eliminates B cells with incompatible H/L pairs.

In this thesis, I introduce a biologically informed negative sampling strategy for H/L pairing classification, drawing on known V-gene biases in heavy and light chain pairing. Pseudo-negatives are constructed by …

Mimic: A Multimodal Dataset For Affective Incongruity In Video, Ethan M. Baird

Computer Science Senior Theses

This thesis investigates the computational challenges of constructing a database for affective incongruity, exploring the difficulties in automating the collection of contradictory affective states. Capturing these incongruities is essential for advancing Vision-Language Models (VLMs) and sentiment analysis, which struggle to interpret signals deviating from basic emotional archetypes. Curating non-congruent affect provides the data necessary for models to navigate complex social contexts, which is critical for applications like automated Audio Description (AD) for the visually impaired and nuanced Human-Computer Interaction (HCI). To capture these signals, two distinct methodologies were employed. The first utilized a tripartite decomposition of video data, isolating textual, …

Representing Lean Proofs: Tactics, Trajectories, Search, Elisaveta Samoylov

Computer Science Senior Theses

In neural theorem proving for interactive proof assistants such as Lean, tactic prediction models score proof steps by surface likelihood, missing whether a move actually advances the proof. This thesis proposes representing each step by the symbolic edit it induces on the proof state rather than by its token-level surface form, and shows that this effect-grounded view yields better tactic embeddings, reveals structured geometry in complete proofs, and enables a practical proof search prior.

We introduce Delta Tokens — token-level state edits augmented with structural indicators — and show they outperform surface-only representations on tactic retrieval and operator-analogy benchmarks. Embedding …

Llzk-Symex: Building A Circuit Verification Framework For The Llzk Zero-Knowledge Intermediate Language, Nicolás Iair Schaievitch

Computer Science Senior Theses

The rising adoption of ZK (Zero-Knowledge) technology has led to a plethora of DSLs (Domain Specific Languages) for facilitating the development of ZK circuits. At the same time, there has also been an increase in the number of compilation targets for these languages, with different cryptographic foundations and performance optimizations. LLZK, by Veridise, aims to unify the ecosystem by providing a single IR (Intermediate Representation) for the different frontend DSLs, that would then also allow choosing between different backends. Given the high stakes (particularly financial) that a lot of ZK circuits are under, together with their high level of complexity, …

Capturing Large Language Model Similarity Through Spectral Analysis, Ishan Verma Prasad

Computer Science Senior Theses

With the rapid development of open-sourced models on Huggingface, there is a strong need for a way to systematically determine the similarity between models. More strongly, for intellectual property and organization, we need a way to determine the "lineage" of models. We borrow principles from Heavy-Tailed Self-Regularization and Random Matrix Theory to provide an inference-free method to accomplish this. We cluster a corpus of several model families by their spectral fingerprints and demonstrate that each model family occupies a distinct region in weight space. This confirms prior ideas of training setups leaving artifacts on model weights and allows us to …

Knockout Tournaments: An Investigation Of Stability, Isabelle Han

Computer Science Senior Theses

Knockout (or single game elimination) tournaments are a competition format widely used to determine a single winner from a pool of participants. However, the seeding, or the initial pairings set by the organizers of the tournament, can dramatically change each participant's probability of winning. This paper introduces stability as a property of tournaments. More specifically, a tournament is stable if no pair of players can be found such that they both wish to swap initial positions. This property is adapted from prior work on stable matchings and is therefore a well-defined structural property.

We investigate three theoretical questions on the …

Reliability-Aware Mixture-Of-Agents For Robust Ai-Generated Image Detection, Jake Jump, Yu-Wing Tai

Computer Science Senior Theses

Detecting AI-generated images requires reasoning across multiple levels of evidence, ranging from low-level statistical artifacts to high-level semantic inconsistencies. Existing approaches typically rely on a single class of signals or emphasize complex multi-agent coordination, which limits robustness under distribution shifts and common image degradations. We propose a reliability-aware Mixture-of-Agents (MoA) framework that treats Vision-Language Model (VLM) agents and computational features as complementary experts and aggregates their predictions based on empirically calibrated reliability. Rather than relying on intricate inter-agent reasoning, our approach centers on structured aggregation: high-precision “anchor” agents drive predictions, while weaker but complementary signals are adaptively incorporated to resolve …

Dancing For The People: A Culturally Grounded Learning-To-Rank Framework For Powwow Dance Evaluation, Avery C. Sutherland

Computer Science Senior Theses

Powwow dance is a form of Indigenous expression that combines movement, storytelling, regalia, and community values. Within competition powwows, dancers are evaluated through a highly subjective judging process that often lacks standardized criteria, creating challenges for consistency, transparency, and fairness. This work investigates whether a learning-to-rank framework can model subjective powwow dance preferences while remaining grounded in the cultural context of the practice. To support this research, a new dataset was constructed consisting of 19 Women's Fancy Shawl dancer profiles and 236 pairwise preference labels collected from experienced members of the powwow community. Each dancer profile combines textual descriptions, images, …

Rscore - A Tool For Learning And Quantifying Software Infrastructure Resiliency, Selena Yujia Zhou

Computer Science Senior Theses

As LLMs take over writing code, infrastructure resilience has become the central challenge of software development, especially for gaming applications, where latency, availability, and scale demands are extreme. However, holistic software infrastructure is difficult to understand for casual developers because of the multiple layers of abstraction that make up an application, and the lack of structured information from proprietary companies. This thesis explores the creation of rscore, a tool that quantifies software infrastructure resiliency and subsequently educates developers about the architecture of any existing gaming application. The tool generates two graphical models of a game’s early versus current infrastructure and …

Ai, Translation, And Telling The Truth, David I. Smith

University Faculty Publications and Creative Works

I am working on a large translation project this year. I have been surprised to find several conversation partners voicing the assumption that I am getting AI to do the translating for me. I’ve been wondering how to respond.

A short, but in the end inadequate answer is that, impressive as the current variations on machine translation are, they still get things wrong. Neural machine translation services such as Google Translate and DeepL still produce oddities fairly regularly. I have been working lately with seventeenth-century Czech texts, an area in which I would expect machine translation to struggle a little …

Holistic Strategies For Optimizing Municipal It Operations And Cost Efficiency, Joseph Yazdanpanahi

Certified Public Manager® Applied Research

Municipalities work to deliver secure and impactful IT (information technology) services while often working within tight budget constraints. To address this problem, this article offers an experience-based and comprehensive framework to optimize municipal IT operations. It emphasizes leveraging automation, streamlining hardware and software management, and forging strategic partnerships to drive cost savings and efficiency gains. Designed to equip municipal IT leaders with practical tools and insights, this article aims to help modernize IT processes.

Residential Ai Data Centers: Security, Privacy, And Governance Concerns, Alan Saquella

Publications

The concept of placing mini data centers and distributed AI computer nodes inside residential homes may appear innovative from an energy efficiency perspective, but it introduces significant security, privacy, governance, and liability concerns. What is effectively occurring is the expansion of commercial and potentially critical infrastructure into lightly protected residential environments.

Once a residence becomes part of a distributed computer grid supporting hyper-scalers, AI providers, or enterprise workloads, the home is no longer simply a private residence. It becomes a commercial technology asset, a potential cyber target, and even a physical target. A distributed network of thousands of residential nodes …

Fairness-Aware And Efficient Federated Learning Frameworks For Heterogeneous Systems, Simin Javaherian

Doctoral Dissertations

Federated Learning (FL) enables decentralized clients to collaboratively train machine learning models without sharing raw data, making it a promising paradigm for privacy-preserving intelligence across large-scale, heterogeneous systems. However, practical FL environments face significant challenges arising from variations in client resources, participation patterns, client behavior, and data distributions. These challenges often lead to inefficiency, unbalanced contributions, and unfairness, ultimately degrading model performance and discouraging long-term client participation. This dissertation advances the state of FL by developing a unified suite of fairness-aware and efficiency-driven frameworks tailored for heterogeneous environments. We investigate fairness from multiple perspectives, including client selection, contribution weighting, and …

Building And Restoring Trust In Deep Learning: From Multimodal Sensing To Generative Synthesis And Model Integrity, Liqun Shan

Doctoral Dissertations

Deep learning has become a foundational technology for modern intelligent systems used in sensing, authentication, media generation, and automated decision-making. As these systems are increasingly deployed in security- and privacy-sensitive settings, ensuring their trustworthiness has become a critical challenge. Yet deep learning models remain vulnerable to spoofed sensory inputs, synthetic media, and malicious behaviors hidden within trained networks. These vulnerabilities undermine reliability and raise serious concerns about whether such systems can be trusted under adversarial and deceptive scenarios. This dissertation investigates how to build and restore trust in deep learning across three tightly connected dimensions: multimodal sensing, generative authenticity, and …

Learning And Predicting The Performance Of Gradual Type System, Mohammad Wahiduzzaman Khan

Doctoral Dissertations

Gradual typing reconciles the complementary strengths of static and dynamic typing by allowing programmers to incrementally introduce type annotations while preserving the flexibility of dynamically typed code. This approach improves reliability, documentation, and tooling support without sacrificing rapid prototyping. To ensure soundness, gradual type systems enforce annotations through runtime checks, typically implemented via cast insertion. Although these checks guarantee correctness, they can introduce substantial and highly variable runtime overhead, making performance prediction and optimization a central challenge for practical adoption. Prior work has largely focused on coarse-grained (macro-level) configurations, where entire modules are either fully typed or untyped. While such …

Scientific Crosstalk: Natural Language Processing, Praveshika Bhandari

Theses and Dissertations

While sentiment analysis has made significant strides in domains such as social media and personal correspondence, its application to formal scientific writings remains under-explored. The crosstalk between emotional expressions in personal and professional communications has also received limited attention despite its potential to reveal insights into the emotional drivers of scientific creativity. Our research introduces a computational framework designed to detect and quantify emotional expressions across various documents over time. Leveraging state-of-the-art transformer models fine-tuned on domain-specific corpora, the framework models emotional tone distribution. Integrating emotion analysis with knowledge graph modeling enables the exploration of emotional trends alongside key scientific …

Reliable Retrieval-Augmented Feature Generation With Large Language Model Reasoning, Jinghan Zhang, Xinhao Zhang, Fengran Mo, Dakshak Keerthi Chandra, Yu-Zhong Chen, Fei Xie, Kunpeng Liu

Computer Science Faculty Publications and Presentations

Feature generation can significantly enhance learning outcomes, particularly for tasks with limited data. An effective way to improve feature generation is to expand the current feature space using existing features and enriching the informational content. However, generating new, interpretable features usually requires domain-specific knowledge on top of the existing features. In this paper, we introduce a Retrieval-Augmented Feature Generation method, RAFG, to generate useful and explainable features specific to domain classification tasks. To increase the interpretability of the generated features, we conduct knowledge retrieval among the existing features in the domain to identify potential feature associations. These associations are expected …

Olaf: Towards Robust Llm-Based Annotation Framework In Empirical Software Engineering, Mia Mohammad Imran, Tarannum Shaila Zaman

Computer Science Faculty Research & Creative Works

Large Language Models (LLMs) are increasingly used in empirical software engineering (ESE) to automate or assist annotation tasks such as labeling commits, issues, and qualitative artifacts. Yet the reliability and reproducibility of such annotations remain underexplored. Existing studies often lack standardized measures for reliability, calibration, and drift, and frequently omit essential configuration details. We argue that LLM-based annotation should be treated as a measurement process rather than a purely automated activity. In this position paper, we outline the Operationalization for LLM-based Annotation Framework (OLAF), a conceptual framework that organizes key constructs: reliability, calibration, drift, consensus, aggregation, and transparency. The paper …

A Large Language Model-Based Analysis Of Vulnerability Discovery In Windows Software, Puya Pakshad, Samson Quaye, Jamal Al-Karaki, Marwan Omar, Maurice E. Dawson

All Works

Source code security auditing is essential before software release in order to identify programming faults that may lead to vulnerabilities and functional failures. In this paper, we present a structured security assessment of the Windows App SDK by integrating multiple static analysis tools with a context-aware and disagreement-aware Large Language Model (LLM) interpretation layer. Although static analyzers are effective in reporting potential weaknesses, their raw outputs often contain redundant alerts, limited contextual explanation, and inconsistent severity assignments. To address these limitations, the proposed LLM-based interpretation layer normalizes and de-duplicates alerts, filters context-limited or nonactionable warnings, and refines severity prioritization under …

Deployment-Aware Deep Learning For Computer Vision: Efficient Architectures From 3d Segmentation To Mixed Reality, Bahar Uddin Mahmud

Dissertations

Deep learning has become the dominant approach for solving vision-centric problems; however, its successful deployment in real-world applications remains limited by high computational cost, data dependency, and insufficient integration with practical and human-centered environments. While state-of-the art deep learning models often achieve impressive performance in controlled settings, they frequently fail to generalize or operate efficiently under deployment constraints such as limited resources, complex data modalities, and real-time interaction requirements. These limitations motivate the need for a deployment-oriented deep learning framework that balances accuracy, efficiency, and practical usability.

This dissertation investigates the design and deployment of efficient deep learning architectures for …

Breadquest: Enhancing Roguelike Accessibility Through Procedural Generation And Thematic Design, Hahns Pena

Computer Science and Software Engineering

BreadQuest is a top-down roguelike dungeon crawler with a whimsical dessert theme that aims to make the genre more accessible while preserving strategic depth and replayability. Players explore procedurally generated dungeons, fight pastry-themed enemies, and collect bakery-inspired items that support a flavor-elemental combat system, with each run offering unique layouts, encounters, and rewards. Built in Unity with a modular, data-driven architecture, the game uses procedural generation techniques like Binary Space Partitioning, Voronoi diagrams, and Perlin noise to create varied and replayable levels. The project emphasizes approachable gameplay, cultural dessert inspiration, and replayability, with success evaluated through playtesting and player feedback.

Real-Time Simulation Of Bio-Luminescent Light Propagation Using Compute Shaders Within Unreal Engine, Jaden D. Halevi

Computer Science Senior Theses

Presented in this paper is a GPU-native approach to interactive fluid simulation within Unreal Engine 5. The system, BioFluidSim, implements an incompressible Navier-Stokes solver using Unreal’s Niagara Grid2D compute shader pipeline, with a modular biological emission output stage parameterized from experimentally measured Lingulodinium polyedrum bioluminescence behavior. The system is evaluated against FluidNinja Live, a commercially available fragment shader fluid implementation, as a performance baseline. Beyond performance, BioFluidSim offers greater physical fidelity than the fragment shader baseline. Helmholtz–Hodge pressure projection enforces a divergence-free velocity field at runtime, a physical constraint approximated but not enforced by fragment shader approaches. The biological emission …

A Systematic Review Of Intrusion Detection Systems For Internet Of Medical Things: Performance, Efficiency, Explainability, And Generalization, Oswald Adohinzin, Youssef Harrath

Research & Publications

The Internet of Medical Things (IoMT) has transformed health care delivery through medical devices, remote patient monitoring, and real-time clinical decision support. However, the proliferation of IoMT devices introduces security vulnerabilities that put patient safety and data privacy at risk. Intrusion Detection Systems (IDS) have emerged as essential components for protecting IoMT networks from cyberattacks. This article presents a systematic review of IoMT-IDS research, analyzing 53 high-quality papers published between 2020 and 2025, identified through database searches spanning 2016–2025 across IEEE Xplore, Springer, ScienceDirect, and ACM Digital Library. We organize the literature through a comprehensive taxonomy spanning classical machine learning …

High-Resolution Queries, Low-Resolution Context: Scaling Vision Transformers With Asymmetric Spatial Reduction, James M. Dwyer

Master's Theses

Vision Transformers (ViTs) have demonstrated great performance on image classifica tion benchmarks, however, the quadratic complexity of the self-attention mechanism with respect to sequence length limits their scalability to higher resolution inputs. The attention score matrix grows as O(N2) in both compute and memory, where N is the number of patch tokens, making ViTs computationally expensive and memory intensive for applications that require real-time inference or operate under resource constraints.

This thesis investigates whether the key and value sequences of the self-attention mechanism can be compressed using the local spatial structure of the image — while keeping queries at full …

Scorespeak: An Agentic System For Natural Language Control Of Musical Scores, Nathan S. Lim

Master's Theses

With the recent popularization of large language models (LLMs), natural language has become one of the most accessible and powerful ways for people to interact with creative tools. Although they have become common in mainstream domains like image and audio editing, there is currently no robust AI-based system that can reliably turn free-form language into edits for symbolic musical scores. This gap represents a missed opportunity to improve human workflows for creating and editing sheet music, but it is also a fundamental limitation for other agentic music systems; without a robust mechanism for translating free-form language into structured scores, AI …