Digital Commons Network^™

Learnable Game-Theoretic Policy Optimization For Data-Centric Self-Explanation Rationalization, Yunxiao Zhao, Zhiqiang Wang, Xingtong Yu, Xiaoli Li, Jiye Liang, Ru Li

Research Collection School Of Computing and Information Systems

Rationalization, a data-centric framework, aims to build self-explanatory models to explain the prediction outcome by generating a subset of human-intelligible pieces of the input data. It involves a cooperative game model where a generator generates the most human-intelligible parts of the input (i.e., rationales), followed by a predictor that makes predictions based on these generated rationales. Conventional rationalization methods typically impose constraints via regularization terms to calibrate or penalize undesired generation. However, these methods are suffering from a problem called mode collapse, in which the predictor produces correct predictions yet the generator consistently outputs rationales with collapsed patterns. Moreover, existing …

Mm-Attackg: A Multimodal Approach To Attack Graph Construction With Large Language Models, Yongheng Zhang, Xinyun Zhao, Yunshan Ma, Haokai Ma, Yingxiao Guan, Guozheng Yang, Yuliang Lu, Xiang Wang

Research Collection School Of Computing and Information Systems

Cyber Threat Intelligence (CTI) parsing aims to extract key threat information from massive data, transform it into actionable intelligence, enhance threat detection and defense efficiency, including attack graph construction, intelligence fusion, and indicator extraction. Among these research topics, Attack Graph Construction (AGC) is essential for visualizing and understanding the potential attack paths of threat events from CTI reports. Existing approaches primarily construct the attack graphs purely from the textual data to reveal the logical threat relationships between entities within the attack behavioral sequence. However, they typically overlook the specific threat information inherent in visual modalities, which preserves key threat details …

The Gains Do Not Make Up For The Losses: A Comprehensive Evaluation For Safety Alignment Of Large Language Models Via Machine Unlearning, Weixiang Zhao, Yulin Hu, Xingyu Sui, Zhuojun Li, Yang Deng, Yanyan Zhao, Bing Qin, Wanxiang Che

Research Collection School Of Computing and Information Systems

Machine Unlearning (MU) has emerged as a promising technique for aligning large language models (LLMs) with safety requirements to steer them forgetting specific harmful contents. Despite the significant progress in previous studies, we argue that the current evaluation criteria, which solely focus on safety evaluation, are actually impractical and biased, leading to concerns about the true effectiveness of MU techniques. To address this, we propose to comprehensively evaluate LLMs after MU from three aspects: safety, over-safety, and general utility. Specifically, a novel benchmark MuBench with 18 related datasets is first constructed, where the safety is measured with both vanilla harmful …

Vercation: Precise Vulnerable Open-Source Software Version Identification Based On Static Analysis And Llm, Yiran Cheng, Ting Zhang, Lwin Khin Shar, Shouguo Yang, Chaopeng Dong, David Lo, Shichao Lv, Zhiqiang Shi, Limin Sun

Research Collection School Of Computing and Information Systems

Open-source software (OSS) has experienced a surge in popularity, attributed to its collaborative development model and cost-effective nature. However, the adoption of specific software versions in development projects may introduce security risks when these versions bring along vulnerabilities. Current methods of identifying vulnerable versions typically analyze and extract the code features involved in vulnerability patches using static analysis with pre-defined rules. They then use code clone detection to identify the vulnerable versions. These methods are hindered by imprecision due to (1) the exclusion of vulnerability- irrelevant code in the analysis and (2) the inadequacy of code clone detection. This paper …

The Feelit System: Application Content-Aware Perspectives And Challenges On Understanding User Likes In Social Network Posts, Konstantinos Theocharidis, Hady W. Lauw, Panagiotis Karras

Research Collection School Of Computing and Information Systems

In a series of our prior works, we study influence and subscription maximization problems in social networks that are based on posts having influential content; as content we consider a set of features where each feature corresponds to a specific social network page, whereas influence and subscription relate to gaining the postlike and subscription-to-brand page of targeted users, respectively; subscription is conceptually achieved as repetitive influence on users. So, both influence and subscription depend on content that gains the likes of users; however, to be realistic, modeling and estimating such likes is a complex problem that has not been adequately …

Exploring Jvm Garbage Collector Testing With Event-Coverage, Kai Zheng, Yingquan Zhao, Junjie Chen, Hanmo You, Haoyu Wang, Haoyu Wang, Tianchang Gao

Research Collection School Of Computing and Information Systems

Garbage Collection (GC) in the Java Virtual Machine (JVM) serves as an automatic memory management mechanism, efficiently reclaiming unused memory space in different production scenarios. To optimize JVM performance, developers typically fine-tune the garbage collector by identifying an optimal set of GC configurations for specific scenarios. Despite the sophisticated design of garbage collectors, they still have the potential for bugs in different settings, and these bugs can result in more severe consequences. Hence, comprehensive testing of these garbage collectors is imperative before their release. Code coverage criteria are typically employed to assess the comprehensiveness of a test suite. However, traditional …

Zero-Shot Video Translation Via Token Warping, Haiming Zhu, Yangyang Xu, Jun Yu, Shengfeng He

Research Collection School Of Computing and Information Systems

With the revolution of generative AI, video-related tasks have been widely studied. However, current state-of-the-art video models still lag behind image models in visual quality and user control over generated content. In this paper, we introduce TokenWarping, a novel framework for temporally coherent video translation. Existing diffusion-based video editing approaches rely solely on key and value patches in self-attention to ensure temporal consistency, often sacrificing the preservation of local and structural regions. Critically, these methods overlook the significance of the query patches in achieving accurate feature aggregation and temporal coherence. In contrast, TokenWarping leverages complementary token priors by constructing temporal …

Cellscout: Visual Analytics For Mining Biomarkers In Cell State Discovery, Rui Sheng, Zelin Zang, Jiachen Wang, Yan Luo, Zixin Chen, Yan Zhou, Shaolun Ruan, Huamin Qu

Research Collection School Of Computing and Information Systems

Cell state discovery is crucial for understanding biological systems and enhancing medical outcomes. A key aspect of this process is identifying distinct biomarkers that define specific cell states. However, difficulties arise from the co-discovery process of cell states and biomarkers: biologists often use dimensionality reduction to visualize cells in a two-dimensional space. Then they usually interpret visually clustered cells as distinct states, from which they seek to identify unique biomarkers. However, this assumption is often this assumption often fails to hold due to internal inconsistencies in a cluster, making the process trial-and-error and highly uncertain. Therefore, biologists urgently need effective …

Prisrv+: Privacy And Usability-Enhanced Wireless Service Discovery With Fast And Expressive Matchmaking Encryption, Yang Yang, Guomin Yang, Yingjiu Li, Pengfei Wu, Rui Shi, Minming Huang, Jian Weng, Hwee Hwa Pang, Deng, Robert H.

Research Collection School Of Computing and Information Systems

The evolution of decentralized identity (DID) and self-sovereign identity (SSI) frameworks, as endorsed by W3C Verifiable Credentials (VC) and eIDAS 2.0, underscores the need for secure, efficient, and privacy-preserving credential management. However, existing credential systems often depend on centralized issuers, lack efficient aggregation mechanisms, or fail to ensure unlinkability across authentication sessions. To address these challenges, we propose DISC (Decentralized Identity System with Self-Sovereign Credential Aggregation), a novel credential system that enables multi-authority credential issuance, user-controlled credential aggregation, and unlinkable authentication. DISC allows users to aggregate credentials from multiple issuers while maintaining constant-size authentication tokens and supporting batch verification for …

How Consistent Friendlike Conversation With Ai Companions Influences Our Attitudes And Perceptions Toward Ai: An Exploratory Experiment, Qi Hui Jerlyn Ho, Meilan Hu, Adalia Yin Hui Goh, Emma Jane Pragasam, Andree Hartanto

Research Collection School of Social Sciences

Despite skepticism and distrust in artificial intelligence (AI), it is increasingly integrated into daily life, with its potential benefits drawing interest. Yet little is known about the attitudinal and psychological effects of human–AI interactions, and whether consistent interactions with AI chatbots can change users’ attitudes and perceptions. Our within-subjects experiment (N = 52) investigated how five days of socially oriented, friendlike interactions with an AI chatbot, versus a journaling control, influenced changes in attitudes and perceptions of AI. Participants’ attitudes towards AI, trust, perceived empathy, anthropomorphism, animacy, likeability, perceived intelligence and safety, dependency, and exploratory well-being indicators were recorded. Results …

Efficient Function Orchestration For Large Language Models, Xiaoxia Liu, Peng Di, Cong Li, Jun Sun, Jingyi Wang

Research Collection School Of Computing and Information Systems

Function calling is a fundamental capability of today's large language models, but sequential function calling posed efficiency problems. Recent studies have proposed to request function calls with parallelism support in order to alleviate this issue. However, they either delegate the concurrent function calls to users for execution which are conversely executed sequentially, or overlook the relations among various function calls, rending limited efficiency. This paper introduces LLMOrch, an advanced framework for automated, parallel function calling in large language models. The key principle behind LLMOrch is to identify an available processor to execute a function call while preventing any single processor …

Atmospheric Circulation Reconstructions Over The Earth (Acre) 2025: Climate Data Recovery, Fiona Williamson

Research Collection College of Integrative Studies

On 15-16 September 2025, Singapore Management University hosted the annual Atmospheric Circulation Reconstructions over the Earth (ACRE, www.met-acre.net/) workshop, ’ACRE 2025: Climate Data Recovery’, chaired by Fiona Williamson, Rob Allan and Praveen Teleti. The 2-day event took place at the College of Integrative Studies and saw around 30 participants from multi-disciplinary backgrounds all working in meteorological data rescue (DaRe, www.community.wmo.int/en/data-rescue-projects-and-initiatives-dare) sharing their latest work and discoveries. Speakers were a mix of climate scientists and historians, archivists and historical climatologists from across the globe. ACRE has been operating for 18 years under Professor Rob Allan, formerly of the UK Meteorological Office …

Final 2022 Unreclaimed Sites Sampling: Ur-12 Site Evaluation Summary Report, Pioneer Technical Services, Inc.

Silver Bow Creek/Butte Area Superfund Site

No abstract provided.

Final 2022 Unreclaimed Sites Sampling: Ur-28 Site Evaluation Summary Reportfinal 2022 Unreclaimed Sites Sampling: Ur-28 Site Evaluation Summary Report, Pioneer Technical Services, Inc.

Silver Bow Creek/Butte Area Superfund Site

No abstract provided.

Anxiety Gets All The Likes, Saniye Nur Ergan

Journal of Humanistic Mathematics

This internet meme (created by me:)) emerges from a simple yet persistent question that underlies much of my work: Why do we continue to treat certain emotions in mathematics as visible, nameable, and research-worthy, while others linger in the background as faint, unarticulated traces?

Being Different Doesn’T Make You Odd, Raffaella Mulas

Journal of Humanistic Mathematics

The number 2 is beautiful and it has many unique properties. It is the only even prime number, and being different from the other prime numbers doesn't make it odd. This is true also for people: being different doesn't make you odd. It makes you beautiful and unique.

Logical Conclusion, Robert Dawson

Journal of Humanistic Mathematics

There is a well-known anecdote about Kurt Gödel, just before his citizenship hearing, telling Einstein that the Constitution was logically flawed. This alternate-history story explored the possible ramifications.

Nightmare In The Library, Charles A. Coppin

Journal of Humanistic Mathematics

Students of real analysis and calculus find that the completeness property of the real numbers is difficult to understand, especially, its importance. The word numbers denote real numbers throughout this piece. After all, the real numbers are not any less imaginary than the so-called imaginary numbers. Although, sometimes, it does gain some mention in calculus courses, its presence as a topic is a mere will-o’-the-wisp of bygone days when teachers would often reach deep into the big ideas of calculus as a mainstay of their courses. For the sake of cultural literacy and the development of mathematical maturity, we believe …

To Those Who Ask "What's The Name Of Your Book, Again?", Marion D. Cohen

Journal of Humanistic Mathematics

No abstract provided.

Yet No Ramanujan, Db Jonas

Journal of Humanistic Mathematics

The poem Yet No Ramanujan conveys the musings of a layman in his garden, obsessed by the way that mundane things, the small experiences of everyday life, suggest the ways in which, as Baudelaire says, "everything is number." This meditation ends with the recognition that the putative stability of a self, a thinking subject, is after all, however complex and unique, like all matter, a kind of oscillation, a complex product of number.

Missing, James S. Huntley

Journal of Humanistic Mathematics

Fifty-five word stories have achieved a certain currency as a reflective format, perhaps especially in medicine. Many of them turn out to be poems. Here is one such story inviting the reader to consider the nature of the absent, of the 'missing', of zero, and the philosophical underpinnings of mathematics.

To The Mysterious Gamma: Euler- Mascheroni Constant, Md Sadikur Rahman

Journal of Humanistic Mathematics

No abstract provided.

Poems For A Calculus Class (After Reading Midlife Calculus And At The Dimensional Border), Kevin Farey

Journal of Humanistic Mathematics

This poetry folder is made up of two short trios. The first begins with “Methods,” a thirteen-line poem by Britt Kaufmann, and continues with two thirteen-line responses to it. The folder’s second half consists of three (non-thirteen-line) responses to a collection of thirteen-line-almost-sonnets by Philip Fried, who had in turn been inspired, during the pandemic, by Edwin Abbot’s Flatland.

Both Kaufmann and Fried are authors of previous JHM poetry folders. Poems from Kaufmann’s book Midlife Calculus appeared in the January 2025 issue and poems from Fried’s series At the Dimensional Border appeared in the July 2024 issue. In addition, …

Plato's God, Vijay Fafat

Journal of Humanistic Mathematics

A poem expressing a thought about recursion in the Platonic Realm, of mathematical archetypes and the dreaming conception of "God"...

The Tool/Weapon Duality Of Mathematics, Alexandre Borovik

Journal of Humanistic Mathematics

This paper outlines the principal moral and ethical issues of mathematics and existential choices a mathematician may face in his professional life. My text is a manifesto; it is a list of declarations rather than a systematic development of the theme. Indeed each section could be expanded into a paper on its own. I hope to write fairly soon a more detailed exposition.

Sumthin: A Context-Dependent African American Vernacular English Word For Variables, Mark Apedo

Journal of Humanistic Mathematics

If mathematics is a language, then African American Vernacular English (AAVE) could hold the key to a fascinating understanding of the evolution of algebra from human speech in North America. The use of the pronoun something (sumthin) to depict an unknown amount of money that varies implies that algebra developed as a logical necessity in human communication. Exploring this phenomenon and leveraging it to demonstrate the concept of algebra could enhance the comprehension of the subject among speakers of AAVE.

The Math Teaching Atlas: Trails, Anchors, And Compass In Action, Ivan Z. Feng

Journal of Humanistic Mathematics

This paper advocates a shift grounded in mathematical reasoning: teach and write math through explicit routeways rather than narratives, anchor new ideas to familiar concepts on a roadmap, and use motivation and concrete examples as a compass and simulation for discovery.

Reminiscences Of My Past Life As A High School Math Teacher, Wayne Nirode

Journal of Humanistic Mathematics

In this article, I reflect on my twenty years as a high school math teacher. I describe four distinct phases of my career in five-year increments. I aim to make public both what makes teaching high school students rewarding and what makes it difficult. Also, my writing illuminates how indelible the first five years were to my development as a teacher. I hope that this brief memoir helps early-career teachers see past the tumultuous beginnings while also inspiring veteran teachers to reflect on their own careers.

Creating Art With The Generalized Pythagorean Theorem, Ángel Colín

Journal of Humanistic Mathematics

The Pythagorean Theorem and its generalizations have been widely studied. In this article we focus on one particular generalization that asserts that the area of a polygon with one side the hypotenuse of a right triangle is the sum of the areas of similar polygons whose corresponding sides are the other two sides [4]. Using this theorem together with interactive software or simply pencil and paper, we create some visually enticing artwork. This activity, we believe, can contribute positively to geometry teaching at all academic levels.

Let's Play Uno! Training Mathematical Thinking With An Inclusive Card Game, Thierry Meyrath, Clara-Ioana Mincu, Antonella Perucca

Journal of Humanistic Mathematics

We explore probability exercises based on the game UNO. Excluding the Wild cards, the deck contains precisely 100 cards, which makes it convenient to express probabilities as percentages. We discuss the mathematical relation between cards that can be played after other cards. We also propose an algebraic exercise that relates several quantities, such as the number of cards left in the losing player’s hand. Finally, we argue that UNO is a very inclusive game: it is logistically easy to play, allows for players of different skill levels, and can be adapted to meet special needs. Beyond being playful exercises, our …