Digital Commons Network^™

Managing Ai Bot Access To Open Scholarly Infrastructures, Petr Knoth

FORCE 2026

The rapid rise of generative AI has created unprecedented demand for large, high-quality research corpora. Open access repositories and other open scholarly infrastructures have therefore become primary sources for AI bots, because they host research that is not universally reliable, but remains far more evidence-based than most web content. This is both an opportunity and a strain: repositories are now more valuable than ever, but machine traffic brings sustainability, capacity and policy challenges. Repositories may be able to scale, but who should fund that scaling, and under what conditions?

The core dilemma is how to curb abusive high-load bot activity …

[Birds-Of-A-Feather] Understanding And Handling Software Plagiarism In The Age Of Generative Ai, Daniel S. Katz, Scott C. Edmunds

FORCE 2026

Computing and software have supported research since their inception, and continue to play a significant role in knowledge production. However, the means of communicating research methods and results were developed long before computing existed, and the research community lacks best practices for documenting computational research elements transparently, reproducibly, and reusably.
Publishers are now more accepting of the inclusion of software (typically, source code) associated with submitted manuscripts, and many want to support processes to vouch for the integrity of software just as they do for other content, such as ensuring that ethical and legal concerns such as authorship, plagiarism, copyrights …

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 …

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 …

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 …

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 …

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 …

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 …

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 …

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 …

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 …

Inductive Biases In Field-Level Cosmological Inference From Galaxy Catalogs, James O'Connor Baldwin

Dissertations, Theses, and Capstone Projects

We perform field-level likelihood-free inference of the matter density parameter Ωm from simulated galaxy catalogs using machine learning models with differing inductive biases. Using features extracted from hydrodynamic simulations in the CAMELS suite, we investigate how both observable choice and model architecture govern the extraction of cosmological information. We consider galaxy positions and line-of-sight peculiar velocities, both separately and in combination, and compare permutation-invariant Deep Sets, implemented with either standard multilayer perceptrons (MLPs) or Kolmogorov–Arnold Networks (KANs), to graph neural networks (GNNs) implemented with MLPs, which explicitly encode spatial relations. We evaluate inference performance under both in-distribution and out-of-distribution (OOD) …

Muon Lifetime: Theory, Experiment, And Simulation, Soren Agustin Munoz

Physics

This senior project investigates the muon lifetime through three complementary approaches: theoretical calculation, laboratory measurement, and computational simulation. The theoretical component develops the necessary background from relativistic field theory to the effective weak interaction, culminating in the leading-order Fermi-theory prediction of τ ≈ 2.2 μs, which explains why the muon lifetime lies on the microsecond scale.

The experimental component measures the lifetime of stopped cosmic-ray muons using a plastic scintillator, photomultiplier tube, and analog timing electronics. A binned Poisson likelihood fit to the primary 15-day acquisition run τ = 2.17^+0.03_-0.09 μs, consistent with the accepted value within the …

Ppg-Sport: A Dataset For Reliable Heart Rate Monitoring From Wrist Ppg Under Dynamic Sports Conditions, Changshuo Hu, Hung Manh Pham, Yiming Zhang, Guanru Yan, Xiao Ma, Yuezhong Wu, Thivya Kandappu, Archan Misra, Dong Ma

Research Collection School Of Computing and Information Systems

Photoplethysmography (PPG) has become a cornerstone of physiological sensing in wearable devices, enabling non-invasive monitoring of heart rate and related biomarkers. However, its reliability deteriorates sharply under dynamic, high-intensity, or non-periodic motions such as those in sports, where existing datasets fail to capture realistic wrist dynamics. To address this gap, we introduce PPG-Sport, the first large-scale dataset designed for heart rate monitoring from wrist-worn PPG under real sports conditions. The PPG-Sport dataset includes synchronized PPG, inertial measurement unit (IMU), and electrocardiography (ECG) recordings from both wrists of 30 participants across six representative activities: stationary, walking, running, badminton, table tennis, and …

“From Remembering To Shaping”: Narrating Shared Experiences By Co-Designing Cultural Heritage Artifacts In Collaborative Vr, Yushang Yang, Fanxu Meng, Fiona Fui-Hoon Nah, L. C. Ray

Research Collection School Of Computing and Information Systems

The ways people remember and recall places reveal an invisible aspect of cultural heritage (CH), reflecting how individuals and communities relate to these places. Heritage is communal, emerging through collaboratively constructed narratives rather than individual records. To probe how people may share collective memories, we designed an immersive two-person workflow for collaboratively co-designing 3D artifacts and environments in virtual heritage locations, using Generative AI (GenAI) to instantiate these intangible memories. Observations of the co-creation process revealed that participants merged prompts and model placements when negotiating different perspectives. They used spatial operations to compose scenes, and also to express personal and …

(R2133) Analysis Of A Bulk Queue With Balking, Adaptive Overloading Service, Multiple Vacation, Inspection And Rework, S. Karpagam, R. Lokesh

Applications and Applied Mathematics: An International Journal (AAM)

We consider a queueing system that utilizes a single server to manage product flow through bulk and overload service modes, depending on queue length. Balking occurs when the queue length reaches ‘N’. After completion of service, products undergo quality inspection, with defective products sent for rework based on specific probabilities. If the product is non-defective, the server continues processing until the queue length exceeds a certain threshold; beyond this point, the server is either routed back to bulk service or directed to an overload service. Also, the server goes into a vacation mode when the queue size is below a …

Legal Ethics Of Ai Snake Oil: Navigating The Hype, Harm, And Hope Of Legal Ai, Drew Simshaw

Michigan Law Review

A review of AI Snake Oil.By Arvind Narayanan and Sayash Kapoor.

Comparing The Sensitivity And Degree Of Boolean Functions Via The Hypercube, Anne-Caroline Rupp

University Honors Theses

This thesis studies three complexity measures of total Boolean functions f:{0,1}ⁿ → {0,1}: maximum sensitivity s(f), polynomial degree deg(f), and spectral sensitivity λ(f), where λ(f) is defined as the spectral norm of the adjacency matrix of the sensitivity graph. Building on the results of Aaronson et al., we examine the inequality chain √s(f) ≤ λ(f) ≤ deg(f) and investigate whether all three quantities can be simultaneously equal.

The first part of the thesis reverse engineers the equality cases of the two known inequalities to isolate necessary extremal conditions on both the Fourier structure of f and the local geometry …

The Security Of Llm-Generated Code, Christopher Brian Gonzalez Ayala

Student Theses

The rapid adoption of Large Language Models (LLMs) in software development has transformed coding practices by enabling automated code generation, completion, and optimization. Despite these advantages, concerns persist regarding the security and reliability of LLM-generated code. This study presents a comprehensive evaluation of both the functional correctness and security of code produced by three prominent LLMs as of early 2026. A total of 4,800 code snippets were generated using 100 security-focused programming prompts derived from the OWASP Top 10:2025, translated across eight natural languages and two phrasing styles (literal and natural developer-oriented prompts). To assess performance, a multi-stage experimental framework …

Adversarial Robustness Of Perceptual Hashing Systems: A Unified Security Evaluation Framework, Avijit Roy

Student Theses

Social network platforms, child safety organizations, and image provenance systems use perceptual hashing to identify known child sexual abuse material (CSAM), support content moderation and reverse image search, and verify image integrity. Perceptual hashing works by producing similar fingerprints for visually similar images, even after common transformations such as compression, resizing, or minor brightness changes. This useful similarity-preserving property also creates an adversarial attack surface, as attackers can use AI-assisted or conventional image manipulation techniques to move a hash across a matching threshold while maintaining visual similarity, often without access to specialized hardware.

The security failures produced by adversarial attacks …

When Saying "No" Is Not Enough: Cognitive-Action Decoupling And The Illusion Of Safety In Llm Agents, Shasha Yu

School of Professional Studies

Current safety evaluations of large language models (LLMs) predominantly rely on textual compliance, implicitly assuming that refusal-style responses correspond to safe behavior. This assumption becomes fragile when LLMs are embedded in agentic systems with the ability to execute state-changing actions. In this paper, we present an empirical critique of text-centric safety evaluation through an action-aware study of LLM agents under controlled conditions. Across multiple state-of-the-art models, we observe a recurring cognitive-action decoupling: agents generate policy-aligned refusal language while still producing unsafe tool-mediated action proposals. This produces an illusion of safety, where conversational audits indicate compliance even as operational risk persists. …

Trace: Temporal Rhetorical Analysis And Consistency Evaluation For Legislative Speech, David Hernandez

Master's Theses

Legislators frequently discuss the same policy issues across multiple hearings and legislative sessions, sometimes maintaining consistent positions and other times modifying or reframing their stance over time. Understanding how these positions evolve is important for analyzing political discourse and democratic accountability, yet identifying such shifts at scale remains difficult.

We introduce TRACE (Temporal Rhetorical Analysis and Consistency Evaluation), a system built on the Digital Democracy Database (DDDB) for detecting rhetorical inconsistency in California legislative hearing testimony. TRACE organizes utterances into speaker-anchored timelines indexed by bill and session, then applies hybrid semantic retrieval — combining dense BGE embeddings with BM25 lexical …