Digital Commons Network^™

Context-Aware Hierarchical Taxonomy Generation For Scientific Papers Via Llm-Guided Multi-Aspect Clustering, Kun Zhu, Lizi Liao, Yuxuan Gu, Lei Huang, Xiaocheng Feng, Bing Qin

Research Collection School Of Computing and Information Systems

The rapid growth of scientific literature demands efficient methods to organize and synthesize research findings. Existing taxonomy construction methods, leveraging unsupervised clustering or direct prompting of large language models (LLMs), often lack coherence and granularity. We propose a novel context-aware hierarchical taxonomy generation framework that integrates LLM-guided multi-aspect encoding with dynamic clustering. Our method leverages LLMs to identify key aspects of each paper (e.g., methodology, dataset, evaluation) and generates aspect-specific paper summaries, which are then encoded and clustered along each aspect to form a coherent hierarchy. In addition, we introduce a new evaluation benchmark of 156 expert-crafted taxonomies encompassing 11.6k …

Prrla Members Digital Preservation Landscape, Pin Pin Yeo, Suqing Liu, Pimnapa Amaritworachai

Research Collection Library

The research aimed to assess the current state of digital preservation practices among PRRLA (Pacific Rim Research Libraries Alliance) member libraries. A literature review on digital preservation in academic libraries was conducted. Information was gathered through surveys and interviews. focusing on policies, staffing, skills, funding, collection maintenance and services related to digital preservation. Additionally, the study explored the role of AI, and future trends in digital preservation. Challenges and best practices for sustainable digital preservation were highlighted.

The Impact Of A Vocational Training ‘Plus’ Programme On Employment And Income, Abu S. Shonchoy, Tomoki Fujii, Selim. Raihan

Research Collection School Of Economics

Following a Randomised Controlled Trial in Northern Bangladesh, this study explores the barriers to rural youth migration to urban employment hubs. By implementing a vocational training “plus” programme facilitating apparel sector employment, the study revealed significant and persistent effects of the programme on income and employment, primarily due to the addition of a stipend and on-the-job training components. Treated participants experienced significant income and remittance increases, alongside reduced income poverty, attributed to the lower job search costs and job–fit risks. Notably, the on-the-job paid apprenticeship offered a benefit–cost ratio of 8.85, demonstrating its cost-effectiveness for programme scalability.

The Motherhood Penalty On Health: Evidence From China, Ang Sun, Fang Xia, Xuan Zhang

Research Collection School Of Economics

Understanding women’s physical and mental well-being following childbirth is critical for informing policies on labor market equity, family support, and fertility. Using event study methods and panel data from China, we document a persistent motherhood penalty in both physical and mental health, whereas the health impacts on fathers are minimal. While mothers experience a temporary reduction in paid work hours, they face a sustained increase in unpaid domestic labor — housework and childcare — resulting in a net increase in total work time. This additional workload likely contributes to deterioration in health. Mothers are also more likely to engage in …

Performances In Last-Mile Deliveries Involving Cyclic Services Of Shuttles And Cargo Bikes, Byung Kwon Lee, Young Joo Kim, Joyce M. W. Low

Research Collection Lee Kong Chian School Of Business

This study introduces a novel approximation model that integrates the ideologies of order statistics and max-plus algebra in representing the collection and distribution service schemes of a last-mile delivery system. Under the respective schemes, electric cargo bikes (e-bikes) perform the last-mile delivery near a microhub with shuttles collecting packages from multiple local logistics hubs (or local hubs, for short) and/or distributing packages to multiple microhubs. The framework is designed to estimate the cyclic capacity under varying cargo carrying capacities of the e-bikes and service network configurations. Real-world data, such as the geographic conditions of the streets around the microhubs in …

Report On Assessing The Digital Preservation Landscape And Capacity Of Prrla Libraries, Pin Pin Yeo, Suqing Liu, Pimnapa Amaritworachai

Research Collection Library

This project evaluated the current state of digital preservation practices among PRRLA (Pacific Rim Research Libraries Alliance) member libraries. This report outlined the best practices and guidelines of the member libraries. The study involved a literature review to examine existing research and practices in digital preservation. A survey was designed to collect detailed information from PRRLA members, complemented by online interviews with selected institutions to gain deeper insights. The report has the key findings, successful strategies with some suggestions for sustainable development of digital preservation.

Delving Into Invisible Semantics For Generalized One-Shot Neural Human Rendering, Yihong Lin, Xuemiao Xu, Huaidong Zhang, Cheng Xu, Weijie Li, Yi Xie, Jing Qin, Shengfeng He

Research Collection School Of Computing and Information Systems

Traditional human neural radiance fields often overlook crucial body semantics, resulting in ambiguous reconstructions, particularly in occluded regions. To address this problem, we propose the Super-Semantic Disentangled Neural Renderer (SSD-NeRF), which employs rich regional semantic priors to enhance human rendering accuracy. This approach initiates with a Visible-Invisible Semantic Propagation module, ensuring coherent semantic assignment to occluded parts based on visible body segments. Furthermore, a Region-Wise Texture Propagation module independently extends textures from visible to occluded areas within semantic regions, thereby avoiding irrelevant texture mixtures and preserving semantic consistency. Additionally, a view-aware curricular learning approach is integrated to bolster the model's …

Cross-Subject Mind Decoding From Inaccurate Representations, Yangyang Xu, Bangzhen Liu, Wenqi Shao, Yong Du, Shengfeng He, Tingting Zhu

Research Collection School Of Computing and Information Systems

Decoding stimulus images from fMRI signals has advanced with pre-trained generative models. However, existing methods struggle with cross-subject mappings due to cognitive variability and subject-specific differences. This challenge arises from sequential errors, where unidirectional mappings generate partially inaccurate representations that, when fed into diffusion models, accumulate errors and degrade reconstruction fidelity. To address this, we propose the Bidirectional Autoencoder Intertwining framework for accurate decoded representation prediction. Our approach unifies multiple subjects through a Subject Bias Modulation Module while leveraging bidirectional mapping to better capture data distributions for precise representation prediction. To further enhance fidelity when decoding representations into stimulus images, …

Classical Shadows With Improved Median-Of-Means Estimation, Winston Fu, Dax Enshan Koh, Siong Thye Goh, Jian Feng Kong

Research Collection School Of Computing and Information Systems

The classical shadows protocol, introduced by Huang et al (2020 Nat. Phys. 16 1050), makes use of the median-of-means (MoM) estimator to efficiently estimate the expectation values of M observables with failure probability δ using only O ( log ⁡ ( M / δ ) ) measurements. In their analysis, Huang et al used loose constants in their asymptotic performance bounds for simplicity. However, the specific values of these constants can significantly affect the number of shots used in practical implementations. To address this, we studied a modified MoM estimator proposed by Minsker (2023 Proc. 36th Conf. on Learning Theory …

Deep Learning For Hate Speech Detection: A Comparative Study, Jitendra Singh Malik, Hezhe Qiao, Guansong Pang, Anton Van Den Hengel

Research Collection School Of Computing and Information Systems

Automated hate speech detection is an important tool in combating the spread of hate speech, particularly in social media. Numerous methods have been developed for the task, including a recent proliferation of deep-learning based approaches. A variety of datasets have also been developed, exemplifying various manifestations of the hate-speech detection problem. We present here a largescale empirical comparison of deep and shallow hate-speech detection methods, mediated through the three most commonly used datasets. Our goal is to illuminate progress in the area, and identify strengths and weaknesses in the current state-of-the-art. We particularly focus our analysis on measures of practical …

Teaching Diffusion Models To Ground Alpha Matte, Tianyi Xiang, Weiying Zheng, Yutao Jiang, Tingrui Shen, Hewei Yu, Yangyang Xu, Shengfeng He

Research Collection School Of Computing and Information Systems

The power of visual language models is showcased in visual understanding tasks, where language-guided models achieve impressive flexibility and precision. In this paper, we ex tend this capability to the challenging domain of image matting by framing it as a soft grounding problem, enabling a single diffusion model to handle diverse objects, textures, and transparencies, all directed by descriptive text prompts. Our method teaches the diffusion model to ground alpha mattes by guiding it through a process of instance-level localization and transparency estimation. First, we introduce an intermediate objective that trains the model to accurately localize semantic components of the …

Impact Of Original Versus Reposted Social Endorsements On Content Consumption: The Moderating Role Of Endorsers’ Network Characteristics, Anqi Zhao, Qian Tang

Research Collection School Of Computing and Information Systems

Social endorsements broadcast endorsers’ positive attitudes toward content or products, especially to their social ties. Original endorsements created by endorsers can be propagated further as reposted endorsements. Both are important marketing tools to increase content consumption, yet their differences are unclear. This study compares the impacts of original and reposted endorsements on content consumption and their contingencies on the endorsers’ network characteristics. Using data on social endorsements of YouTube videos on Twitter, we find that original endorsements (i.e., original tweets) significantly boost content consumption, and the effect is positively moderated by the endorsers’ network size but not their tie strength. …

Robust Contracting Under Distributional Uncertainty, Jiangtao Li, Kexin Wang

Research Collection School of Economics

We study contract design when the principal has limited information about the output distributions induced by the agent's actions. In a baseline model where only the means are known, we show that increasing affine contracts are robustly optimal. The mean restrictions accommodate a wide range of output distributions, including extreme cases that help establish this optimality. We then extend the analysis to environments with additional constraints on the distributions. Our main result shows that the robust optimality of increasing affine contracts persists even when the principal knows more—for example, that each action induces a distribution with full support.

A Comprehensive Review Of Financial Knowledge Graphs, Jeyaraman Brindha Priyadarshini, Bing Tian Dai, Yuan Fang

Research Collection School Of Computing and Information Systems

Knowledge Graphs (KGs) are increasingly used in finance to manage complex, interconnected data and support advanced analytics. This survey provides an overview of how KGs are applied across various financial areas, such as fraud detection, credit risk assessment, anti-money laundering, and regulatory compliance. We examine key techniques for building and using KGs in finance, including graph construction, embedding methods, and machine learning models. The survey also discusses challenges specific to finance, like handling private data, ensuring interpretability, and managing real-time data. Additionally, we explore the emerging combination of KGs with large language models and generative AI, which offers new possibilities …

Lsfdnet: A Single-Stage Fusion And Detection Network For Ships Using Swir And Lwir, Yanyin Guo, Runxuan An, Junwei Li, Zhiyuan Zhang

Research Collection School Of Computing and Information Systems

Traditional ship detection methods primarily rely on single-modal approaches, such as visible or infrared images, which limit their application in complex scenarios involving varying lighting conditions and heavy fog. To address this issue, we explore the advantages of short-wave infrared (SWIR) and long-wave infrared (LWIR) in ship detection and propose a novel single-stage image fusion detection algorithm called LSFDNet. This algorithm leverages feature interaction between the image fusion and object detection subtask networks, achieving remarkable detection performance and generating visually impressive fused images. To further improve the saliency of objects in the fused images and improve the performance of the …

Parameter-Efficient Variational Autoencoder For Multimodal Multi-Interest Recommendation, Nhu Thuat Tran, Hady Wirawan Lauw

Research Collection School Of Computing and Information Systems

Learning user preferences in recommendation systems is enriched by multimodal features, such as textual and visual content, and amplified by multi-interest modeling with Variational AutoEncoders (VAEs). However, prior efforts are limited by single modality focus and cumbersome, parameter-heavy architecture designs. To address these limitations, we introduce an innovative solution that blends the semantic richness of multimodal data with the representational power of multi-representation VAEs. Drawing inspiration from Mixture of Experts (MoE), we cast each VAE as an expert tailored to a specific modality, then fuse them via a novel parameter-merging function into a lean, unified model. This approach efficiently captures …

Search Trajectory Network-Enhanced Multi-Objective Dynamic Algorithm Configuration, Robbert Reijnen, Zaharah Bukhsh, Hoong Chuin Lau, Yaoxin Wu, Yingqian Zhang

Research Collection School Of Computing and Information Systems

Deep reinforcement learning (DRL) has emerged as an effective technique for dynamic algorithm configuration, particularly in evolutionary computation, enabling adaptive parameter updates during algorithmic execution. DRL-based methods have shown broad applicability across different problem domains and are designed to configure algorithms without problem-specific information, making them highly transferable across problem variants and scalable to different problem sizes. This paper proposes a novel graph neural network-based approach that learns representations of Search Trajectory Networks (STNs) to track the convergence behavior of multiple objectives and dynamically reconfigures multiobjective evolutionary algorithms during execution. By capturing how solutions evolve and interact over time, the …

Lightweight Population-Based Policy Optimization For Pickup And Delivery Problems, Yizhou Liu, Li Li, Yixin Xu, Tang Liu, Rong Cheng, Die Wu, Jilin Yang, Jingwen Li

Research Collection School Of Computing and Information Systems

In recent years, applying deep models to automatically learn construction heuristics for vehicle routing problems has achieved remarkable advancements. However, they are less effective in searching solutions due to two primary limitations: relying on deterministic probability distributions and overlooking the strategic advantage of prioritizing nearby unvisited nodes during the route construction process, resulting in suboptimal policies In this paper, we propose a novel lightweight population-based policy optimization (LPPO) framework that learns a diverse population of solution strategies through the utilization of innovative perturbation factors, in order to facilitate search exploration. Moreover, we design a localized attention synthesis (LAS) network to …

Contrastrepair: Enhancing Conversation-Based Automated Program Repair Via Contrastive Test Case Pairs, Jiaolong Kong, Xiaofei Xie, Mingfei Cheng, Shangqing Liu, Xiaoning Du, Qi Guo

Research Collection School Of Computing and Information Systems

Automated Program Repair (APR) aims to automatically generate patches for rectifying software bugs. Recentstrides in Large Language Models (LLM), such as ChatGPT, have yielded encouraging outcomes in APR,especially within the conversation-driven APR framework. Nevertheless, the efficacy of conversation-drivenAPR is contingent on the quality of the feedback information. In this article, we propose ContrastRepair, anovel conversation-based APR approach that augments conversation-driven APR by providing LLMs withcontrastive test pairs. A test pair consists of a failing test and a passing test, which offer contrastive feedback tothe LLM. Our key insight is to minimize the difference between the generated passing test and the …

Morphology-Aware Hrv Estimation From Wrist Ppg In Sedentary Scenarios, Changshuo Hu, Hung Manh Pham, Dong Ma

Research Collection School Of Computing and Information Systems

Photoplethysmography (PPG) is widely used in wearable devices for non-invasive heart rate variability (HRV) monitoring. While most prior work focuses on mitigating motion artifacts, recent studies highlight that even subtle contact pressure variations can distort waveform morphology and lead to inaccurate HRV estimates. In this work, we propose a morphology-aware deep learning framework that conditions HRV estimation on beat-level waveform types. Our model jointly encodes the raw PPG waveform and a sequence of pressure-induced morphology labels using parallel encoders, integrates them via cross-attention, and predicts normal-to-normal (NN) intervals and beat count to support downstream HRV computation. Evaluated on the public …

Polyqent: A Polynomial Quantified Entailment Solver, Krishnendu Chatterjee, Amir Kafshdar Goharshady, Ehsan Kafshdar Goharshady, Mehrdad Karrabi, Milad Saadat, Maximilian Seeliger, Dorde Zikelic

Research Collection School Of Computing and Information Systems

Polynomial quantified entailments with existentially and universally quantified variables arise in many problems of verification and program analysis. We present PolyQEnt which is a tool for solving polynomial quantified entailments in which variables on both sides of the implication are real valued or unbounded integers. Our tool provides a unified framework for polynomial quantified entailment problems that arise in several papers in the literature. Our experimental evaluation over a wide range of benchmarks shows the applicability of the tool as well as its benefits as opposed to simply using existing SMT solvers to solve such constraints.

Adolescent Executive Function As A Resilience Factor In The Family Stress Model Among Mexican-Origin Families, Su Yeong Kim, Yayu Du, Tianlu Zhang, Jingyi Shen, Kiera M. Coulter, Lester Sim, Wen Wen, Belem G. Lopez, Maria M. Arredondo, Shen Yishan, Hou Yang

Research Collection School of Social Sciences

Mexican-origin families often face economic hardship due to systemic oppression, increasing the likelihood of adolescent marijuana use. While the family stress model provides insight into the mechanism of the association between family economic hardship and adolescent marijuana use, resilience factors are relatively unknown. The present study uses a three-wave longitudinal data set of Mexican immigrant families in the United States (Wave 1—adolescents: Mage = 12.29, SD = 0.93; mothers: Mage = 38.57, SD = 5.71) to investigate the mechanism underlying the association between family income and adolescents’ likelihood of marijuana use, guided by the family stress model. The protective role …

A 3-Item Short Version Of The Fear Of Missing Out (Fomo) Scale For Trait And Time-Intensive Designs: Measurement Invariance And Psychometric Properties, Eva M. Hisham, Andree Hartanto, Nadyanna M. Majeed

Research Collection School of Social Sciences

Research on Fear of Missing Out (FoMO) has gained prominence alongside the rise of digital connectivity and social media, which offer individuals continuous access to others’ experiences in real time. Importantly, it has been increasingly recognised as an important psychological construct, closely associated with various problematic digital behaviours. As the fields of media psychology and human-computer interaction increasingly adopt time-intensive methodologies (e.g., daily and weekly studies) to capture dynamic experiences of technology use, there is a growing need for brief yet psychometrically-sound measures of FoMO suitable for such designs. The present work reports the development of a 3-item FoMO scale …

Product Technology Adoption And Aggregate Innovation, Qiugu He, Xuan Luo, Fan Zheng

Research Collection School Of Economics

We document that a firm's research and development (R&D) expenditure depends on its product diversity. Combining with the fact that Chinese manufacturers often enter new product markets via technology adoption, we develop a quantitative framework of innovation and technology adoption, allowing firms to expand their product scopes. Firms adopt technologies across multiple fields to expand their knowledge base, which in turn serves as an input for subsequent innovation or adoption. Counterfactual analysis from the 2000s reveals that two-thirds of knowledge privately held by all firms is generated through adoption, accounting for one-third of aggregate innovation.

Southeast Asia Higher Education Changes And Emerging Futures, Muhammad Hali Aprimadya, Lily Kong, Angel Calderon, Hamish Coates

Research Collection School of Social Sciences

This paper unpacks recent developments and future directions in Southeast Asian higher education. It takes stock of higher education systems in three selected countries, Australia, Indonesia and Singapore. It sketches these systems, distils several changes around 2024, and discusses emerging directions for education, research and universities. The paper concludes by looking at what is required to catalyse transformations likely to impel future progress.

Everyday Norms Have Become More Permissive Over Time And Vary Across Cultures, K. Eriksson, P. Strimling, I. Vartanova, Andree Hartanto

Research Collection School of Social Sciences

Every social situation that people encounter in their daily lives comes with a set of unwritten rules about what behavior is considered appropriate or inappropriate. These everyday norms can vary across societies: some societies may have more permissive norms in general or for certain behaviors, or for certain behaviors in specific situations. In a preregistered survey of 25,422 participants across 90 societies, we map societal differences in 150 everyday norms and show that they can be explained by how societies prioritize individualizing moral foundations such as care and liberty versus binding moral foundations such as purity. Specifically, societies with more …

Personality And Personnel Selection: Going Beyond Self-Reports And Linear Relationships, Filip Lievens, Jinyan Fan, Jingyi Li

Research Collection Lee Kong Chian School Of Business

The study of personality in selection and assessment represents one of the most longstanding and voluminous literature in industrial and organizational psychology. In this paper, we review two important recent research streams. First, we review studies on alternatives to self-report personality inventories, namely the use of Situational Judgment Tests (SJTs), assessment center (AC) exercises, and a multi-rater framework. Second, we review studies that go beyond linear relationships between personality and job performance. Generally, our review reveals that these alternative approaches show promises in better understanding personality and how personality relates to performance.

Harnessing Se Community Knowledge For Developer-Centric Code Intelligence, Chengran Yang

Dissertations and Theses Collection (Open Access)

The integration of Large Language Models (LLMs), particularly those tailored for programming tasks—referred to as code LLMs—has created novel opportunities to enhance developer productivity. These advanced models automate routine and repetitive coding tasks, such as code generation and debugging, and enable faster prototyping and more efficient problem-solving. Despite these remarkable advantages, the current generation of code LLMs exhibits notable limitations that impact their practical effectiveness in real-world software engineering scenarios. These models frequently produce code that is inefficient or suboptimal in runtime performance, demonstrate opaque reasoning processes, and struggle to adapt effectively to diverse developer contexts and specific requirements. Moreover, …

Factors Influencing Consumers’ Online Purchase Decisions: Evidence From Amazon.Com, Weiwei Li

Dissertations and Theses Collection (Open Access)

With the rapid expansion of cross-border e-commerce, platform sellers increasingly adopt diverse price formatsto influence consumer decision-making. In this context, consumers’ perceptions of and responses to price information have become a pivotal issue in understanding online purchase behavior. Using Amazon as the research setting, this study employs a dynamic panel model with monthly product-level data spanning January 2024 to June 2025 to investigate how different price formats—such as Prime-exclusive pricing and coupon mechanisms—affect consumers’ online purchase intentions when the out-ofpocket price is held constant. Furthermore, the moderating effect of promotional events is systematically examined.

Departing from prior research that largely …

The Role Of Employee Engagement In Predicting Risk Management Outcome, Jenny Tan

Dissertations and Theses Collection (Open Access)

Risk performance is a key business performance indicator as it measures how well an organization manages its uncertainties. Well-balanced risk performance instills confidence in stakeholders (including investors) and improves organizational performance broadly speaking. This dissertation studies the relationship between Perceived Organizational Support, employee engagement and risk appetite and how that relates downstream to organisational risk performance. Using the lens of Social Exchange Theory (SET; Blau, 1964) I examine how perceived organizational support (POS) predicts employee engagement and how this then relates to risk appetite and subsequent levels of risk taking in an organization. I then make predictions about how exchange …