arXiv subjects

Harry Wang

Publications and source records attributed to Harry Wang.

8 recordsLinked to original sources

arXiv2026

Stochastics of News Article Propagation: Joint Modeling of Counts and Reliability Composition in Event-Driven News Cascades

We study the news cascade triggered by a single high-impact event as a pair of coupled stochastic processes: the daily article count $N(t)$ and the reliable-vs-unreliable composition $\pi_{\mathrm{pos}}(t)$. Using the 2017 Las Vegas shooting as a primary case study (CC-News + NewsGuard, 91 days, 2,702 articles), we fit and compare four counting-process models for $N(t)$ and four distributional models for $\pi_{\mathrm{pos}}(t)$ on a common likelihood scale. For counts, a hybrid Inhomogeneous-Poisson plus Hawkes model wins decisively on AIC, BIC, and log-likelihood, as the IHP accounts for the initial exogenous shock, while the Hawkes accounts for the subsequent self-excitation. A profile-likelihood sweep of the Hawkes decay rate collapses the optimal Hawkes kernel to an AR(1) one-step lag $\lambda(t)=\mu+nN(t-1)$. This Markovian structure on the counts directly motivates the Part-B reliability models: we treat the reliability label as a first-order Markov chain on a binary state space and test homogeneous, regime-switching, and mean-field parameterizations against a bivariate Hawkes baseline model using a shared conditional binomial likelihood. The results show that the bivariate Hawkes model and the non-homogeneous Markov models are nearly indistinguishable on fit, as they exhaust the signal and start fitting to the noise. A brief replication on the 2017 Hurricane Harvey data shows that the same methodology applies but produces different results due to Hurricane Harvey's gradual endogenous build-up.

stat.AP↗

arXiv2026

Seeing the Evidence, Missing the Answer: Tool-Guided Vision-Language Models on Visual Illusions

Vision-language models (VLMs) exhibit a systematic bias when confronted with classic optical illusions: they overwhelmingly predict the illusion as "real" regardless of whether the image has been counterfactually modified. We present a tool-guided inference framework for the DataCV 2026 Challenge (Tasks I and II) that addresses this failure mode without any model training. An off-the-shelf vision-language model is given access to a small set of generic image manipulation tools: line drawing, region cropping, side-by-side comparison, and channel isolation, together with an illusion-type-routing system prompt that prescribes which tools to invoke for each perceptual question category. Critically, every tool call produces a new, immutable image resource appended to a persistent registry, so the model can reference and compose any prior annotated view throughout its reasoning chain. Rather than hard-coding illusion-specific modules, this generic-tool-plus-routing design yields strong cross-structural generalization: performance remained consistent from the validation set to a test set containing structurally unfamiliar illusion variants (e.g., Mach Bands rotated from vertical to horizontal stacking). We further report three empirical observations that we believe warrant additional investigation: (i) a strong positive-detection bias likely rooted in imbalanced illusion training data, (ii) a striking dissociation between pixel-accurate spatial reasoning and logical inference over self-generated annotations, and (iii) pronounced sensitivity to image compression artifacts that compounds false positives.

cs.CV↗

arXiv2026

Story2Proposal: A Scaffold for Structured Scientific Paper Writing

Generating scientific manuscripts requires maintaining alignment between narrative reasoning, experimental evidence, and visual artifacts across the document lifecycle. Existing language-model generation pipelines rely on unconstrained text synthesis with validation applied only after generation, often producing structural drift, missing figures or tables, and cross-section inconsistencies. We introduce Story2Proposal, a contract-governed multi-agent framework that converts a research story into a structured manuscript through coordinated agents operating under a persistent shared visual contract. The system organizes architect, writer, refiner, and renderer agents around a contract state that tracks section structure and registered visual elements, while evaluation agents supply feedback in a generate evaluate adapt loop that updates the contract during generation. Experiments on tasks derived from the Jericho research corpus show that Story2Proposal achieved an expert evaluation score of 6.145 versus 3.963 for DirectChat (+2.182) across GPT, Claude, Gemini, and Qwen backbones. Compared with the structured generation baseline Fars, Story2Proposal obtained an average score of 5.705 versus 5.197, indicating improved structural consistency and visual alignment.

cs.CL↗

arXiv2026

Verifiable Error Bounds for Physics-Informed Neural KKL Observers

This paper proposes a computable state-estimation error bound for learning-based Kazantzis--Kravaris/Luenberger (KKL) observers. Recent work learns the KKL transformation map with a physics-informed neural network (PINN) and a corresponding left-inverse map with a conventional neural network. However, no computable state-estimation error bounds are currently available for this approach. We derive a state-estimation error bound that depends only on quantities that can be certified over a prescribed region using neural network verification. We further extend the result to bounded additive measurement noise and demonstrate the guarantees on nonlinear benchmark systems.

eess.SY↗

arXiv2026

Idea2Story: An Automated Pipeline for Transforming Research Concepts into Complete Scientific Narratives

Autonomous scientific discovery with large language model (LLM)-based agents has recently made substantial progress, demonstrating the ability to automate end-to-end research workflows. However, existing systems largely rely on runtime-centric execution paradigms, repeatedly reading, summarizing, and reasoning over large volumes of scientific literature online. This on-the-spot computation strategy incurs high computational cost, suffers from context window limitations, and often leads to brittle reasoning and hallucination. We propose Idea2Story, a pre-computation-driven framework for autonomous scientific discovery that shifts literature understanding from online reasoning to offline knowledge construction. Idea2Story continuously collects peer-reviewed papers together with their review feedback, extracts core methodological units, composes reusable research patterns, and organizes them into a structured methodological knowledge graph. At runtime, underspecified user research intents are aligned to established research paradigms, enabling efficient retrieval and reuse of high-quality research patterns instead of open-ended generation and trial-and-error. By grounding research planning and execution in a pre-built knowledge graph, Idea2Story alleviates the context window bottleneck of LLMs and substantially reduces repeated runtime reasoning over literature. We conduct qualitative analyses and preliminary empirical studies demonstrating that Idea2Story can generate coherent, methodologically grounded, and novel research patterns, and can produce several high-quality research demonstrations in an end-to-end setting. These results suggest that offline knowledge construction provides a practical and scalable foundation for reliable autonomous scientific discovery.

cs.CE↗

arXiv2023

Using Language Models to Detect Alarming Student Responses

This article details the advances made to a system that uses artificial intelligence to identify alarming student responses. This system is built into our assessment platform to assess whether a student's response indicates they are a threat to themselves or others. Such responses may include details concerning threats of violence, severe depression, suicide risks, and descriptions of abuse. Driven by advances in natural language processing, the latest model is a fine-tuned language model trained on a large corpus consisting of student responses and supplementary texts. We demonstrate that the use of a language model delivers a substantial improvement in accuracy over the previous iterations of this system.

cs.CL↗

arXiv2022

A Weakly-Supervised Iterative Graph-Based Approach to Retrieve COVID-19 Misinformation Topics

The COVID-19 pandemic has been accompanied by an `infodemic' -- of accurate and inaccurate health information across social media. Detecting misinformation amidst dynamically changing information landscape is challenging; identifying relevant keywords and posts is arduous due to the large amount of human effort required to inspect the content and sources of posts. We aim to reduce the resource cost of this process by introducing a weakly-supervised iterative graph-based approach to detect keywords, topics, and themes related to misinformation, with a focus on COVID-19. Our approach can successfully detect specific topics from general misinformation-related seed words in a few seed texts. Our approach utilizes the BERT-based Word Graph Search (BWGS) algorithm that builds on context-based neural network embeddings for retrieving misinformation-related posts. We utilize Latent Dirichlet Allocation (LDA) topic modeling for obtaining misinformation-related themes from the texts returned by BWGS. Furthermore, we propose the BERT-based Multi-directional Word Graph Search (BMDWGS) algorithm that utilizes greater starting context information for misinformation extraction. In addition to a qualitative analysis of our approach, our quantitative analyses show that BWGS and BMDWGS are effective in extracting misinformation-related content compared to common baselines in low data resource settings. Extracting such content is useful for uncovering prevalent misconceptions and concerns and for facilitating precision public health messaging campaigns to improve health behaviors.

cs.HC↗

arXiv2017

Two-stage Plant Species Recognition by Combining Local K-NN and Weighted Sparse Representation

In classical sparse representation based classification and weighted SRC algorithms, the test samples are sparely represented by all training samples. They emphasize the sparsity of the coding coefficients but without considering the local structure of the input data. To overcome the shortcoming, aiming at the difficult problem of plant leaf recognition on the large-scale database, a two-stage local similarity based classification learning method is proposed by combining local mean-based classification method and local WSRC. In the first stage, LMC is applied to coarsely classifying the test sample. nearest neighbors of the test sample, as a neighbor subset, is selected from each training class, then the local geometric center of each class is calculated. S candidate neighbor subsets of the test sample are determined with the first smallest distances between the test sample and each local geometric center. In the second stage, LWSRC is proposed to approximately represent the test sample through a linear weighted sum of all samples of the candidate neighbor subsets. The rationale of the proposed method is as follows: the first stage aims to eliminate the training samples that are far from the test sample and assume that these samples have no effects on the ultimate classification decision, then select the candidate neighbor subsets of the test sample. Thus the classification problem becomes simple with fewer subsets; the second stage pays more attention to those training samples of the candidate neighbor subsets in weighted representing the test sample. This is helpful to accurately represent the test sample. Experimental results on the leaf image database demonstrate that the proposed method not only has a high accuracy and low time cost, but also can be clearly interpreted.

stat.AP↗